browser-use-tool changedagents-and-tools/tool-use/browser-use-tool
Nearest release: v2.1.286, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+4added
Lines−4removed
From line
285
where the diff opens
First seen
20 Aug 2026
this site's first read of the page
Recorded edits12to this page, all time
The whole hunk
from line 285, old and new numbered
/
from line 285
285285Browser use runs as an agent loop in your application: Claude returns member tool calls, your executor runs them against the browser, and you return the results until Claude answers in text.
286286
287287<Steps>
288 <Step title="Provide Claude with the browser use tool and a user prompt" icon="tool">
288 <Step title="Provide Claude with the browser use tool and a user prompt">
289289 * Add the `browser_toolset_20260801` entry, and optionally other tools, to your API request.
290290 * Include a user prompt that calls for working with webpages, for example, "Open example.com/docs and tell me how to get started."
291291 </Step>
292292
293 <Step title="Claude responds with member tool calls" icon="wrench">
293 <Step title="Claude responds with member tool calls">
294294 * Claude returns one or more `tool_use` blocks in a single assistant turn; several in one turn form a batch action, for example, `left_click`, then `type`, then `key`.
295295 * Each block's `name` is the member name, each carries `"toolset_name": "browser"`, and `input` holds only that member's parameters, with no `action` field. The response's `stop_reason` is `tool_use`.
296296 </Step>
297297
298 <Step title="Run the calls in order and return results" icon="browser">
298 <Step title="Run the calls in order and return results">
299299 * Iterate every `tool_use` block in `response.content` (don't assume there's exactly one) and run them sequentially, in the order they appear, because later calls usually depend on earlier ones.
300300 * Return one `tool_result` per block in a new `user` message, matched by `tool_use_id`, and echo `"toolset_name": "browser"` on each. Every call must be answered or the next request is rejected.
301301 * If a call fails, return `is_error: true` with a text description for that block, then apply the halt rule in [Batch actions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#batch-actions) to every later block in the turn.
302302 </Step>
303303
304 <Step title="Claude continues until the task is complete" icon="arrows-clockwise">
304 <Step title="Claude continues until the task is complete">
305305 * Claude reads the results (page text, accessibility trees, screenshots, tab state) and, if it needs more, returns further member calls, which takes you back to step 3.
306306 * Otherwise, it returns a text response to the user.
307307 </Step>
No line in this hunk matches that.