Open a URL and return a structured snapshot of the page's interactive elements.

Get a structured snapshot of the current page — each interactive element has a stable id you can act on. Cached until the page changes.

Return ONLY what changed since your last snapshot (added/removed/changed elements). Cheaper than a full snapshot — prefer this after an action.

Find interactive elements matching a description (e.g. 'search box', 'Sign in button') and get just the matches with their ids — far cheaper than reading a full snapshot when you know what you want.

Return the visible text content of the current page (truncated).

Go back in the browser history.

Click an element by its snapshot id. Returns a fresh snapshot after the action.

Type text into a field by its snapshot id (clears the field first).

Return console logs and page errors captured on the current page.

Return the network responses (status, method, url) captured on the current page.

Run a JavaScript EXPRESSION in the page and return its JSON-serialized result (e.g. document.title or [...document.links].length). Not a statement body.

Extract all links on the page as name/href pairs.

Close and discard the current browser session; the next action starts a fresh one. Use to recover from a wedged or crashed page.