> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.runtype.com/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.runtype.com/_mcp/server. # Built-in tools Runtype provides built-in tools that an Agent or Flow can call without any code. The following table lists the core tools, their IDs, and the models that they work with: | Tool | ID | What it does | Compatible models | | -------------------- | ------------------------------ | --------------------------------------------------------------------- | ---------------------------------------------------- | | GPT Image 2.5 | `builtin:gpt-image-2-5` | Generate images from text | Any model | | OpenAI Web Search | `builtin:openai_web_search` | Search the web for current information | OpenAI GPT-4o and GPT-5 models | | Anthropic Web Search | `builtin:anthropic_web_search` | Search the web for current information | Claude Opus 4.x, Claude Sonnet 4.x, Claude Haiku 4.5 | | Anthropic Web Fetch | `builtin:anthropic_web_fetch` | Fetch and read content from a URL | Claude Sonnet 4.x | | xAI Web Search | `builtin:xai_web_search` | Search the web for current information | Grok 4 models | | xAI X Search | `builtin:xai_x_search` | Search X posts | Grok 4 models | | Google Search | `builtin:google_search` | Ground answers in Google Search results | Selected Gemini 2.5, 3, and 3.1 models | | Exa | `builtin:exa` | Search the web with neural and keyword search | Any model | | Firecrawl | `builtin:firecrawl` | Scrape and extract web page content | Any model | | Massive Web Render | `builtin:massive` | Fetch pages that resist ordinary requests | Any model | | Semantic Search | `builtin:vector-search` | Search knowledge bases by meaning | Any model | | Decision judgment | `builtin:decision_judge` | Ask typed yes-or-no, one-of-N, or scored questions about text or JSON | Any model | Choose a tool marked **Any model** when you want to use it with different model providers. A provider-native tool works only with the models listed for it. The tool picker hides it for every other model. The Anthropic tools don't list Claude Sonnet 5 or Claude Opus 5, so the picker hides them for those models. To search the web with a 5-series Claude model, use Exa or Firecrawl. OpenAI Web Search, Anthropic Web Search, xAI Web Search, xAI X Search, and Google Search each add a per-search fee to the model token costs. Review these charges under **Cost by built-in tool** in [Usage data](/user-guide/settings/usage-data). ## Other built-in tools Runtype also provides the following tools. The tool picker groups them by category: | Picker category | Tools | What they do | | --------------- | ------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------ | | **Browser** | `builtin:browser:*` | Interact with live web pages. See [Browser tools](#browser-tools). | | **Records** | Upsert Record, Batch Upsert Records, Get Record, List Records, Delete Record | Create, read, update, and delete [Records](/user-guide/records/what-are-records). | | **Records** | Save to Memory, Recall from Memory, Get Memory Summary | Store and recall information across conversations. See [Agent Memory tools](#agent-memory-tools). | | **Records** | Propose Skill | Draft an [Agent Skill](/user-guide/agents/agent-skills) and submit it for review. | | **File ops** | Store Asset, Publish Page, Generate PDF | Store files, publish HTML pages, and render PDFs. See [File operations](#file-operations). | | **Messaging** | Send Email | Send transactional email. See [Send Email](#send-email). | | **Sandbox** | `builtin:sandbox:*` | Run commands and code, edit files, check out Git repositories, and expose ports in a Linux sandbox. | | **Commerce** | `builtin:ucp_*` | Browse catalogs, manage carts, and check out on merchant sites that support the Universal Commerce Protocol (UCP). | | **Artifacts** | Emit Artifact (Markdown), Emit Artifact (Component) | Stream Markdown or components to supported clients. See [Artifact tools](/user-guide/agents/agent-tools#artifact-tools). | | **Time** | Get Current Time, Convert Time Between Zones, Time Difference, Set Conversation Timezone, Set Reminder | Work with time zones and schedule reminders. See [Temporal tools](#temporal-tools). | The **Sandbox** category tools work in any Agent or Flow. Each call runs in `/workspace`. To keep one sandbox across calls, start it with `sandbox:create` and pass its `sandboxId` to the `sandbox:session_*` tools. For the Linux computer that you turn on for an Agent, see [Agent Sandbox tools](#agent-sandbox-tools). ## Before you begin Add the required provider keys before you configure a tool: * **GPT Image 2.5**: Use a Runtype platform key or add an OpenAI API key in **Settings > Models**. * **OpenAI Web Search**: Add an OpenAI API key in **Settings > Models**. * **Anthropic Web Search** and **Anthropic Web Fetch**: Add an Anthropic API key in **Settings > Models**. * **xAI Web Search** and **xAI X Search**: Use a Runtype platform key or add an xAI API key in **Settings > Models**. * **Google Search**: Use a Runtype platform key or add a Google API key in **Settings > Models**. * **Exa**: Use a Runtype platform key or add an Exa API key in **Settings > Integrations**. * **Firecrawl**: Use a Runtype platform key or add a Firecrawl API key in **Settings > Integrations**. * **Massive Web Render**: If the tool is enabled for your account, use a Runtype platform key or add a Massive API key in **Settings > Integrations**. * **Semantic Search**: Add an OpenAI API key in **Settings > Models** for embeddings. If you need background on vector data, see [What are Records?](/user-guide/records/what-are-records). * **Decision judgment**: Credentials depend on the selected decision model. Jev through Vercel uses your organization's gateway key or eligible Runtype platform funding. Native OpenAI Decisions requires your organization's OpenAI key, without platform fallback. Cloudflare uses eligible Runtype platform funding. See [Decision models](/user-guide/flows/judgments#decision-models). * **Send Email**: No key is needed to send from the platform-managed sender. To send from your own domain, add a Resend API key in **Settings > Integrations**. ## Add tools to an Agent To add built-in tools to an Agent, follow these steps: 1. Open the Agent. 2. In the tools strip, click **Add tool**, or press Cmd+T (Ctrl+T on Windows). The tool picker opens. 3. Select the tools to attach. The picker groups tools by category, such as **Web search** and **Images**, and lists only tools that are compatible with the Agent's model. 4. Optional: If a tool shows **Set up**, click **Set up**, enter its settings, and click **Save**. 5. Close the tool picker and save the Agent. For the other tool types and the full Agent setup, see [Agent tools](/user-guide/agents/agent-tools). ## Add tools to a Flow To add built-in tools to a Flow, follow these steps: 1. Open the Flow and add or edit a prompt step. 2. On the step, click the tools button. It shows **No tools** until you attach a tool. The tool picker opens. 3. Select the tools to attach. The picker lists only tools that are compatible with the step's model. 4. Optional: If a tool shows **Set up**, click **Set up**, enter its settings, and click **Save**. 5. Click **Save** to apply the tools to the step, then save the Flow. For a complete Flow walkthrough, see [Creating and editing flows](/user-guide/flows/creating-and-editing-flows). ### Invoke a built-in tool directly with a Tool Call step A prompt step lets the model decide when to call a tool. When the call must happen at a fixed point every run, use a [Tool Call step](/user-guide/flows/flow-step-types-overview#tool-call) instead and set its `toolId` to the catalog ID: ```json { "type": "tool-call", "name": "Store the report", "config": { "toolId": "builtin:store_asset", "parameters": { "url": "{{reportUrl}}", "filename": "report.pdf" }, "outputVariable": "storedAsset" } } ``` `toolId` accepts any built-in or platform catalog ID (`builtin:store_asset`, `builtin:browser:open`, `builtin:slack:send_message`, `platform:orthogonal::`) as well as a saved Tool. To supply per-tool settings, use the optional `config.toolConfig` object. It takes the same values that a prompt step's tool configuration collects. > **Note** > > A Tool Call step is deterministic and has **no approval gate**: it runs whenever the Flow reaches it, with the parameters you wrote. A step on `builtin:send_email` or a `builtin:browser:*` tool sends and browses unattended. Approval gating applies to model-chosen tool calls in an Agent or a prompt step. ## Test a tool To check that a tool works before you attach it, run it directly. The following request runs Exa with a search query: ```bash curl -X POST https://api.runtype.com/v1/tools/builtin:exa/execute \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"parameters": {"query": "Cloudflare Workers pricing"}}' ``` Replace `YOUR_API_KEY` with your Runtype API key. A successful call returns the tool's `result` with its `toolId` and `toolName`. To pass a tool's settings, add a `toolConfig` object beside `parameters`. The `runtype` CLI runs the same call: ```bash runtype tools execute builtin:exa --input '{"query": "Cloudflare Workers pricing"}' ``` Use `--config` to pass tool settings as JSON. To look up tool IDs and parameters, use these endpoints: * `GET /v1/tools/builtin`: list every built-in tool. * `GET /v1/tools/builtin/compatible?model=YOUR_MODEL_ID&provider=YOUR_PROVIDER`: list the tools that work with a model. For example, set `model` to `claude-haiku-4-5` and `provider` to `anthropic`. * `GET /v1/tools/builtin/YOUR_TOOL_ID/schema`: get one tool's parameter schema and default configuration. Replace `YOUR_TOOL_ID` with a tool ID, such as `builtin:exa`. In an Agent definition, list the IDs in `tools.toolIds` and put per-tool settings in `tools.toolConfigs`, keyed by the same ID. For an example, see [Decision judgment](#decision-judgment). ## Require approval for tools that act for you Some built-in tools act outside Runtype. Send Email sends real email, Browser tools act on live sites, and UCP Complete Checkout starts a real purchase. To pause an Agent until a person approves these calls, add them to the Agent's tool approval list. The following configuration requires approval for email, every Browser tool, and checkout: ```json { "tools": { "approval": { "require": [ "builtin:send_email", "builtin:browser:*", "builtin:ucp_complete_checkout" ] } } } ``` For the dashboard setting and how each Surface shows the prompt, see [Safety](/user-guide/agents/creating-and-configuring-agents#safety). ## GPT Image 2.5 Use GPT Image 2.5 to generate images from text in an Agent conversation or Flow. The tool returns a generated image that you can view or download. The following settings control image generation: | Setting | Values | Default and behavior | | ------------- | -------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Size | `auto` or custom `WxH` | Defaults to `1024x1024`. Both edges must be multiples of 16, the longer edge can be up to 3840 pixels, the aspect ratio must be between 1:3 and 3:1, and the total pixel count must be from 655,360 to 8,294,400. | | Quality | `auto`, `low`, `medium`, `high`, `xhigh`, or `max` | Defaults to `low`. Low quality takes about 10 seconds. Medium and high quality can take 1 to 3 minutes or longer. The `xhigh` and `max` tiers cost more and take longer than `high`. | | Output format | `png`, `jpeg`, or `webp` | Defaults to `png`. | | Background | `auto`, `opaque`, or `transparent` | Defaults to `auto`. A transparent background requires an output format of `png` or `webp`. On `jpeg`, the tool falls back to an opaque background. | If you request a resolution outside those size bounds, the tool adjusts it to the nearest accepted resolution and keeps the orientation you asked for. A request for a wide banner stays wide: a `1200x400` banner is scaled up to `1424x480` rather than squared to `1024x1024`. For example, ask an Agent to "Create a logo for a coffee shop." The Agent calls GPT Image 2.5 and returns the generated image. Runtype stores a permanent copy of each generated image and returns its hosted URL. If storage fails, the tool returns the original image URL or media content and the execution continues. The earlier tool IDs `builtin:gpt-image-2` and `builtin:dalle` remain accepted, and both run on GPT Image 2.5. They no longer appear in the tool picker. Use `builtin:gpt-image-2-5` for new configurations. ## OpenAI Web Search Use OpenAI Web Search with a compatible OpenAI model to retrieve current information from the web during a conversation. Configure these settings: * **Search context size**: Set the context size to `low`, `medium`, or `high`. * **Location context**: Optionally set a city and region for location-specific search results. ## Anthropic Web Search Use Anthropic Web Search with Claude Opus 4.x, Claude Sonnet 4.x, or Claude Haiku 4.5 to retrieve current information from the web. Configure **Max uses** as a number from 1 to 10. The default is `5`. ## Anthropic Web Fetch Use Anthropic Web Fetch with a Claude Sonnet 4.x model to fetch and read content from a specific URL. Use it when your prompt includes a known URL for retrieval. Configure **Max uses** as a number from 1 to 10. The default is `1`. ## xAI Web Search Use xAI Web Search with a compatible Grok model to search the live web during a conversation. Grok can issue multiple searches during one response. Configure these optional settings: * **Allowed domains**: Restrict results to specific domains. * **Excluded domains**: Omit results from specific domains. * **Enable image understanding**: Let the model interpret images in search results. ## xAI X Search Use xAI X Search with a compatible Grok model to search posts on X. Grok can issue multiple searches during one response. Configure these optional settings: * **Allowed X handles**: Restrict results to posts from specific handles. * **Excluded X handles**: Omit posts from specific handles. * **From date** and **To date**: Limit results to an ISO 8601 date range. * **Enable image understanding**: Let the model interpret images in posts. * **Enable video understanding**: Let the model interpret videos in posts. ## Google Search Use Google Search with a compatible Gemini model to ground a response in Google Search results. Gemini decides when to search, writes its own queries, and returns inline citations. The compatible models are Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 3 Flash, Gemini 3 Pro Preview, Gemini 3.1 Pro, and Gemini 3.1 Flash-Lite. Configure these optional settings: * `includeImageSearch`: Also ground on Google Image Search results. The default is `false`. * `fromDate` and `toDate`: Limit results to an ISO 8601 time window. Set both values, with `fromDate` earlier than `toDate`. If you set only one, the tool applies no window. ## Exa Use Exa with any model to search the web with neural or keyword search. Configure optional full text, summaries, highlights, domain filters, and publication-date filters. Configure these settings: * **Search type**: Select `auto`, `neural`, or `keyword`. * **Number of results**: Return from 1 to 10 results. The default is `5`. * **Content options**: Include full text, AI-generated summaries, or highlights. * **Domain filtering**: Include or exclude specific domains. * **Date filtering**: Limit results to a publication date range. Use domain filtering to focus research on selected websites, such as documentation sites. ## Firecrawl Use Firecrawl with any model to extract content from a web page. Firecrawl renders JavaScript pages and returns Markdown, HTML, raw HTML, screenshots, or links. Configure these settings: * **Output formats**: Select Markdown, HTML, raw HTML, screenshots, or links. * **Main content only**: Keep this setting enabled to remove sidebars, navigation, and footers from the result. * **Wait time**: Add from 0 to 30 seconds for dynamic content to load before scraping. Use Firecrawl to extract a product page as Markdown for summarization or analysis. ## Massive Web Render Use Massive Web Render with any model to fetch pages that resist ordinary HTTP requests. It renders JavaScript, solves CAPTCHAs, retries requests through a residential network, and supports country-based fetching. The tool returns Markdown by default, rendered HTML, or raw HTML. Massive Web Render appears only when it is enabled for your account. For setup details, see [Massive (web rendering)](/user-guide/integrations/massive-web-render). Configure these settings: * **Output format**: Select `markdown`, `rendered`, or `raw`. The default is `markdown`. * **Country**: Enter a two-letter ISO country code, such as `us`. * **Delay**: Add from 0.1 to 10 supplemental seconds before the tool captures content. Use Massive Web Render when a page returns a 403 response to ordinary requests and you need the rendered content. ## Semantic Search Use Semantic Search with any model to find content in a knowledge base by meaning rather than exact keywords. Add multiple Semantic Search instances to the same Agent or Flow when you need to search different knowledge bases. Semantic Search supports three providers: Platform Records (pgvector), Weaviate, and Cloudflare Vectorize. Each instance points to one knowledge base, which must already hold embedded content. To load and tune a knowledge base, see [Building retrieval that works](/user-guide/records/building-retrieval-that-works). To connect Weaviate, see [Weaviate (vector search)](/user-guide/integrations/weaviate-vector-search). ### Set up a knowledge base instance To add a Semantic Search instance, follow these steps: 1. In the tool picker, find **Semantic Search** and click **Set up**. 2. In **Display name**, enter a name such as `Search Documentation`. The model uses this name when it selects the instance. 3. In **Provider**, select **Platform Records (pgvector)**, **Weaviate**, or **Cloudflare Vectorize**. 4. Identify the knowledge base. For Platform Records, select a **Record type**. For Weaviate, enter the **Class name**. For Cloudflare Vectorize, enter the **Index name**. 5. Set the **Similarity threshold** from `0` to `1`. Lower values return more results. Higher values return closer matches. 6. Click **Save**. The `limit` setting controls the maximum number of results per query. Set it from 1 to 20. The default is `5`. Start with a similarity threshold near `0.3` and adjust it based on result quality. A high threshold can omit relevant content. A low threshold can return noisy results. ## Decision judgment Agents using any chat model can call Decision judgment to ask typed questions about text or JSON state and get back probabilities, labels, and scores instead of prose. Select a supported decision model separately for the question set. The stable tool ID is `builtin:decision_judge`. For what a judgment is and how to act on one, see [Judgments](/user-guide/flows/judgments). ### Configure an instance A configured instance references a published question set, and the Agent or step supplies only `state`. Add several instances to the same Agent or Flow when you ask different question sets. The following table lists the instance settings: | Setting | Required | Description | | --------------- | -------- | ------------------------------------------------------------------------------------- | | `questionSetId` | Yes | The `qset_` ID of a question set with a published version. | | `version` | No | A published version number. Leave it empty to use the current published version. | | `model` | No | The judgment model ID. Leave it empty to use the question set's model or the default. | | `displayName` | No | The name that the model sees, such as `Ticket triage`. | This prompt step configuration adds one instance named `triage`: ```json { "tools": { "toolIds": ["builtin:decision_judge#triage"], "toolConfigs": { "builtin:decision_judge#triage": { "questionSetId": "qset_YOUR_QUESTION_SET_ID", "displayName": "Ticket triage" } } } } ``` Replace `qset_YOUR_QUESTION_SET_ID` with the ID of your question set. The questions on a configured instance are locked to the referenced question set. A call that also sends `questions` is refused, so the model can't rewrite the rubric. The tool resolves the model in this order: the instance's `model`, then the question set's `model`, then the default, `typesafe-ai/jev`. To run a configured instance outside an Agent or Flow, send the same settings as `toolConfig` to `POST /v1/tools/builtin:decision_judge/execute`, with `{ "state": ... }` as `parameters`. The response adds `metadata.judgment` with the resolved model, token usage, and estimated cost. For the request and the fields, see [Call a configured instance over REST](/user-guide/flows/judgments#call-a-configured-instance-over-rest). An exported Agent or Flow also runs the tool in a self-hosted runtime. The export embeds the question set of each configured instance. For the credentials and key modes, see [Run judgments in a self-hosted runtime](/user-guide/flows/judgments#run-judgments-in-a-self-hosted-runtime). ### Call the tool ad hoc Without a `questionSetId`, the tool is ad hoc: the model supplies inline `questions` beside `state` on each call. Use it when the question changes from call to call, such as checking one claim against one piece of evidence. A tool configuration can't carry inline questions. Save them as a question set instead. ## Agent Memory tools Enable Agent Memory to store facts, preferences, decisions, and events across conversations. Unlike Semantic Search, which queries a knowledge base, Agent Memory stores information associated with an Agent Memory profile. Runtype also records each user and assistant exchange in the background. Agent Memory works with any model and does not need an API key. To enable Agent Memory, set `memory: { enabled: true }` in the Agent configuration. For profile scoping and the complete configuration, see [Memory](/user-guide/agents/creating-and-configuring-agents#memory). Runtype adds these tools when memory is enabled: | Tool | What it does | | ------------------ | ------------------------------------------------------------------------------------------------ | | Save to Memory | Store a fact, preference, or observation as a sentence. You can scope it to a session. | | Recall from Memory | Search memory by meaning and return a synthesized answer with scored candidate memories and IDs. | | Get Memory Summary | Return a Markdown summary of key facts, recent events, active tasks, and standing instructions. | Configure `recall_memory` with these optional parameters: * `thinkingLevel`: Set the search breadth to `low`, `medium`, or `high`. * `responseLength`: Set the synthesized answer length to `short`, `medium`, or `long`. When memory is not enabled for an Agent, the memory tools return `memory_not_enabled` instead of failing silently. ## Browser tools Use Browser tools in an Agent or Flow to interact with live web pages. They appear in the **Browser** category and support quick actions, persistent sessions, and autonomous browsing. ### Quick actions Quick-action tools run against one URL without keeping a session open. Use them to retrieve content from a page and finish the browser operation in one call. * `browser:screenshot`: Capture a screenshot of a rendered page. * `browser:content`: Return the fully rendered HTML after JavaScript runs. * `browser:markdown`: Convert a rendered page to Markdown. * `browser:scrape`: Extract data from CSS selectors on a rendered page. * `browser:json`: Extract structured JSON from a rendered page. * `browser:links`: Retrieve links from a rendered page. * `browser:snapshot`: Return rendered HTML and a screenshot together. ### Session tools Session tools share a persistent browser session across turns in the same conversation. Use `browser:open` to start a session, then pass its `sessionId` to the other session tools. * `browser:open`: Start a session and load a URL. * `browser:navigate`: Navigate to a URL in the session. * `browser:click`: Click an element. * `browser:type`: Type into an input. * `browser:scroll`: Scroll the page. * `browser:session-screenshot`: Capture the current session view. * `browser:evaluate`: Run a script against the page. * `browser:session-info`: Read the current session state. * `browser:close`: End the session. Sessions close after 2 minutes of inactivity and have a 10-minute maximum lifetime. Finish multi-step work within that window. ### Hand a session to a person Hand a browser session to a person when the page needs a login, multi-factor authentication, CAPTCHA completion, payment, or another human decision. Do not share credentials with a browser tool. * `browser:get_live_view`: Return a Live View URL that opens the page in a browser tab. Anyone with the URL can control the page, so share it only with the intended person. * `browser:request_handoff`: Return a Live View URL and instructions for a person. The tool returns immediately. The person selects **Done** or **Failed** in Live View when the task ends. * `browser:get_handoff_state`: Return whether the handoff is active or complete, including the person's success result. Set a handoff timeout from 30 seconds to 30 minutes. The default is 10 minutes. While a handoff is active, the session's inactivity timer and maximum lifetime are paused. Each session supports up to 10 handoffs and 60 minutes of total handoff time. After you call `browser:request_handoff`, share the Live View URL and poll `browser:get_handoff_state` until its status is `completed`. If the handoff reports failure, use `browser:session-screenshot` to confirm the page state before continuing. ### Autonomous browsing with `browser:agent` Use `browser:agent` when you want a browser tool to complete a web task from a natural-language goal. Provide a `startUrl` for a new session or a `sessionId` from `browser:open` for an existing session. Configure the result with these options: * **Start a session**: Set `startUrl`. * **Use an existing session**: Set `sessionId`. * **Choose the output**: Set `outputSchema` for structured JSON. Without it, the tool returns a text summary. Session tools use flat per-action billing. `browser:agent` uses dynamic billing based on usage, with the default account margin of 20%. `browser:agent` plans its steps with Gemini 3.5 Flash Lite through the Runtype model gateway on Runtype's platform credentials, so the page content the task reads is sent to Google. Gemini tokens are billed at catalog rates plus the account margin and appear under **Browser agent** in usage. The task runs on Cloudflare Workers AI instead when any of these apply: * The organization uses BYOK-only model credentials or zero data retention. * The organization's platform spend is blocked. * The organization has its own Google or Vercel AI Gateway key. Browser tasks never use your own model keys. ### Limit where browser tools can go To restrict the sites a Browser tool can load, add a `domainPolicy` to that tool's configuration in the Agent's `toolConfigs`: ```json { "tools": { "toolIds": ["builtin:browser:open", "builtin:browser:agent"], "toolConfigs": { "builtin:browser:open": { "domainPolicy": { "allowedDomains": ["example.com", "*.example.com"], "blockedDomains": ["ads.example.com"] } }, "builtin:browser:agent": { "domainPolicy": { "allowedDomains": ["*.example.com"] } } } } } ``` * An entry is a bare hostname. `example.com` matches only that host. `*.example.com` matches its subdomains but not `example.com` itself, so list both to allow both. * A host that matches `blockedDomains` is always blocked. When `allowedDomains` is set, every host that it does not match is blocked. `allowedDomains` accepts at most 50 entries. * The policy applies to every page load in the browser, including links the model clicks, redirects, scripts, images, and popups. A popup that opens on a blocked host is closed. * A session keeps the policy of the `browser:open` call that started it. A `domainPolicy` on a session action (`browser:navigate`, `browser:click`, `browser:type`, `browser:scroll`, `browser:session-screenshot`, `browser:evaluate`, or `browser:agent` with a `sessionId`) can narrow that session's policy but cannot widen it. The narrowed policy applies to every later call in that session. * `browser:session-info`, `browser:close`, `browser:get_live_view`, `browser:request_handoff` and `browser:get_handoff_state` load no page, so saving a `domainPolicy` on them fails. Set the policy on `browser:open` instead. * Only the tool configuration sets the policy. A tool call whose arguments include `domainPolicy` fails, so a model cannot change the policy. * Quick-action tools apply the policy to the requested `url` and to every request the page makes. A policy replaces any `allowRequestPattern` in the call and adds its blocked hosts to any `rejectRequestPattern`. ## File operations Use File Operations tools in an Agent or Flow to store files, publish pages, and generate PDFs. They appear in the **File ops** category. ### Store an asset Use `store_asset` to store a file from an HTTP or HTTPS URL or from base64-encoded content. The tool returns a public URL or a time-limited signed URL. Stored files are served as downloads instead of rendered inline. Configure `store_asset` with these parameters: | Parameter | Required | Description | | ------------- | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | | `url` | One of `url` or `content` | HTTP or HTTPS URL of the file to store, or a `runtype-asset://` handle from another tool's result in the same execution | | `content` | One of `url` or `content` | Base64-encoded file content. A `runtype-asset://` handle placed here also resolves to the stored bytes, but `url` is the shorter path. | | `contentType` | With `content` | MIME type for inline content, such as `image/png` | | `filename` | No | Filename for the stored file | | `visibility` | No | Set `public` for a public URL or `private` for a time-limited signed URL. The default is `public`. | Pass exactly one of `url` or `content`. Files have a 25 MB size limit. To publish HTML that renders in a browser, use `publish_page` instead. ### Pass media between tools When a tool returns binary media, such as a `browser:session-screenshot` PNG, a generated image, or a text-to-speech clip, Runtype stores the bytes and adds a `runtype-asset://` handle to the tool result. The model sees the image and the handle in the same turn. On later turns, the transcript keeps only the handle, so the model never re-types the base64 content. To pass the media to another tool, the Agent puts the handle in a parameter instead of the bytes: * **`store_asset` and `publish_page`**: accept the handle in the `url` parameter. The bytes are read from storage server-side, not downloaded. * **Base64 parameters**: any parameter whose schema declares `contentEncoding: "base64"` resolves a handle to the stored bytes before the tool runs. Built-in examples are `store_asset.content`, `publish_page.content`, and `send_email.attachments[].content`. Custom external and MCP tools can declare the same keyword; see [Receive binary results from other tools](/developer-guides/guides/runtime-tools#receive-binary-results-from-other-tools). Handles are scoped to your organization and expire after 7 days. The same behavior applies on every execution path: Agent turns, Flows, `execute_tool` on the REST API and MCP server, and Code Mode. When the chain needs logic between hops, such as a loop or a branch, use Code Mode. ## Send Email Use Send Email (`builtin:send_email`) to send transactional email through Resend from an Agent or Flow. It works with any model. The tool sends real email, so consider requiring approval for it. For the setting, see [Require approval for tools that act for you](#require-approval-for-tools-that-act-for-you). The following table describes the parameters: | Parameter | Required | Description | | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | | `to` | Yes | One or more recipient addresses, separated by commas | | `subject` | Yes | Subject line | | `html` | One of `html` or `text` | HTML body. You can send both `html` and `text`. | | `text` | One of `html` or `text` | Plain-text body | | `from` | No | Sender address. Leave it blank to use the platform-managed sender. A custom address requires your own Resend API key and a verified domain. | | `cc` | No | CC recipients, separated by commas | | `bcc` | No | BCC recipients, separated by commas | | `replyTo` | No | Reply-To address | | `attachments` | No | Files to attach. Each item takes a `filename`, a base64 `content` value or a `runtype-asset://` handle, and an optional `contentType`. | To attach a file that another tool produced, pass its handle as the attachment `content`. For details, see [Pass media between tools](#pass-media-between-tools). ## Temporal tools Use Temporal tools when your Agent needs a current time, a time-zone conversion, an elapsed-time calculation, a stored conversation time zone, or a reminder. These tools work with any model and do not need an API key. The following table describes the Temporal tools: | Tool | What it does | | -------------------------- | ------------------------------------------------------ | | Get Current Time | Return the current date and time in an IANA time zone | | Convert Time Between Zones | Convert a wall-clock time between IANA time zones | | Time Difference | Calculate the elapsed time between two instants | | Set Conversation Timezone | Store a time zone for the conversation | | Set Reminder | Schedule a one-time Agent run with a follow-up message | When you omit a time zone, Runtype uses the explicit tool parameter, the Agent's default time zone, the conversation's stored time zone, or UTC. Set the Agent's default time zone in the [`temporal` configuration](/user-guide/agents/creating-and-configuring-agents#temporal-awareness). ### Set a reminder Use **Set Reminder** to schedule a one-time run of the same Agent. The scheduled Agent receives the `message` value when the reminder fires and can act on it, including sending a message or email. Configure the reminder with these parameters: | Parameter | Required | Description | | ----------- | -------------------------- | --------------------------------------------------------------------------------- | | `message` | Yes | Instruction that the scheduled Agent receives | | `at` | One of `at` or `inSeconds` | Absolute fire time in RFC 3339 or ISO 8601 format, such as `2026-06-04T09:00:00Z` | | `inSeconds` | One of `at` or `inSeconds` | Relative delay in seconds, such as `3600` for one hour | | `timezone` | No | IANA time zone for a zone-less `at` value | **Set Reminder** is available only to Agents. Reminders count toward your plan's active schedule limit, along with schedules created in the dashboard or API. For more information, see [Plan limits](/user-guide/schedules/what-are-schedules#plan-limits). ## Control media visibility Set the `mediaVisibility` setting in a tool configuration to control whether the end user and the model receive media produced by that tool. The following values control media visibility: | Value | End user receives media | Model receives media | | ------- | ----------------------- | -------------------- | | `user` | Yes | No | | `model` | No | Yes | | `both` | Yes | Yes | The default is `both`. Use `model` for an intermediate image that the model uses for reasoning. Use `user` for media that you want to display without adding it to the model's context. ## Agent Sandbox tools To give an Agent a Linux computer, turn on **Linux computer** in the Agent's **Sandbox** section. This applies to an Agent that runs on a Runtype model, not to an external agent. To turn on the sandbox and set its persistence, network access, setup commands, and secrets, see [Sandbox](/user-guide/agents/creating-and-configuring-agents#sandbox). When the sandbox is on, Runtype adds these tools to the Agent: * `bash`: run a shell command in `/workspace`. * `bash_output`: read new output from a running command. * `kill_process`: stop a running process and its child processes. * `list_processes`: list running and recently finished processes. * `read_file`: read a file from the sandbox. * `write_file`: write a file to the sandbox. * `edit_file`: edit a file in the sandbox. * `expose_port`: expose a sandbox port through a public preview URL. By default, the sandbox can reach only package registries, OS mirrors, and GitHub. A `bash` command that calls any other host fails. To reach more hosts, add them to `networkAccess.allow` or choose another network profile. The `bash` tool runs in `/workspace`. Its `timeout_ms` value sets when the tool returns control, not when it stops the command. Runtype caps `timeout_ms` at 30,000 milliseconds, or 240,000 milliseconds when `slow_ok` is `true`. If the command continues, the result includes a `process_id`, partial output, and a running status. When a command returns a `deliveryId`, pass that value as `ack_delivery_id` to the next `bash_output` call. Use `wait_for_exit_ms` to wait for the process to finish instead of polling in a loop. The tool caps the wait at 240,000 milliseconds. Use `list_processes` to check processes without replaying their output. Use `kill_process` to stop a process, then call `bash_output` to read any remaining output. Files you write to `/workspace` remain available to later calls in the same execution. The sandbox keeps files, not running processes. After the sandbox shuts down, a process does not resume. ### Coding-agent sessions When `config.sandbox.codingAgents` lists a coding agent, the Agent can hand a task to that coding agent inside the sandbox and follow its progress as a typed session. `opencode` is the only supported coding agent. The Agent gets six more tools: * `agent_session_start`: start the coding agent on a task. Set `mode` to `build` to let it edit files, or `plan` to ask for a plan without edits. * `agent_session_prompt`: send a follow-up message after the previous prompt stops. * `agent_session_status`: read the current digest of a session. * `agent_session_events`: page through the session's recorded events. * `agent_session_cancel`: stop the running prompt. The session stays open for a later prompt. * `list_agent_sessions`: list sessions with their status, for example to recover a `session_id`. Each session tool returns a compact digest instead of raw output. The digest holds the session status, the plan, recent tool titles, counters, a short tail of the latest text, and a `deliveryId`. Tool arguments, tool results, file contents, and reasoning never appear in it. A typical loop works like this: 1. Call `agent_session_start` with a `task` and a `wait_ms` value. The tool waits inside the sandbox, up to 240,000 milliseconds, instead of returning at once. 2. To keep waiting, call `agent_session_status` with the previous `deliveryId` as `ack_delivery_id`, plus `wait_ms`. The acknowledgement moves the digest window forward. If you omit it, the tool replays the unacknowledged digest, so a lost call drops nothing. 3. When `status` is `stopped`, read `finalText` for the result. It appears once, on the digest that first reports the stop. 4. To check the actual changes, run `git diff` with the `bash` tool. For more detail, page `agent_session_events` from `offset` 0 and continue from `nextOffset`. Use `wake_on` to choose which events end a wait early: `stop` (the prompt finished), `pending` (a permission request awaits a decision), or `plan` (a plan step changed). The default is `stop` and `pending`. The event log keeps a limited number of events. Each event keeps tool titles, kinds, statuses, file locations, and short message text. It does not keep tool arguments, tool results, file contents, or reasoning. A workspace policy answers the coding agent's permission requests. An edit, delete, or move must declare a location under the session's working directory, or the policy rejects it. Shell commands, reads, and searches are allowed. If `agent_session_start` times out, retry it with the same `session_id`. An existing id resumes that session instead of starting a second one. > **Warning** > > Everything the coding agent reports is untrusted output. Check its claims, for example with `git diff`, before you rely on them. ## Use platform keys or your own API keys Runtype provides platform keys for several tools that Runtype runs for you, such as Exa and Firecrawl. Platform keys are shared and rate-limited. Use them for development and lower-volume workloads. Connect your own API keys in **Settings** when you need dedicated rate limits or direct provider billing. For a comparison, see [Platform keys vs. bring your own key (BYOK)](/user-guide/getting-started/platform-keys-vs-byok). ## Troubleshoot built-in tools The following issues are the most common: * **A tool doesn't appear in the picker**: The Agent or prompt step uses a model that the tool doesn't support. Check the model against the table at the start of this page, or run the compatible-tools request in [Test a tool](#test-a-tool). Massive Web Render also appears only when it is enabled for your account. * **A tool returns "API key not configured"**: No key is available for that provider. For example, Exa returns `Exa API key not configured. Please add your Exa API key in Settings > Integrations.` Add the key where the message says. Semantic Search returns a similar error when no OpenAI key is available for embeddings. * **A sandbox command can't reach a host**: The sandbox network profile blocks the host. Add the host to `networkAccess.allow`, as described in [Agent Sandbox tools](#agent-sandbox-tools). ## Best practices Use these practices when you configure tools: * **Describe tool use**: Tell your Agent when and how to use each tool. * **Limit result counts**: Set a result limit that matches the task. * **Combine tools**: Pair Exa with Firecrawl for research, or pair Semantic Search with a prompt step for retrieval workflows. * **Use multiple knowledge bases**: Configure separate Semantic Search instances for different data sources, such as documentation and customer Records. ## Next steps Follow these links to continue: * [What are Tools?](/user-guide/tools/what-are-tools): compare built-in, custom, and external tools. * [Agent tools](/user-guide/agents/agent-tools): attach tools to an Agent and write tool descriptions. * [Connecting AI model providers](/user-guide/integrations/connecting-ai-model-providers): configure provider keys for tools that require them. * [Available AI models](/user-guide/settings/available-ai-models): review model compatibility for provider-native tools. * [Resend (email sending)](/user-guide/integrations/resend-integration): send email from your own domain through Resend. * [Cloudflare (Vectorize and Browser Rendering)](/user-guide/integrations/cloudflare-integration): connect Cloudflare Vectorize and Browser Rendering. * [Granola integration](/user-guide/integrations/granola-integration): connect Granola and use meeting notes in Agents and Flows.