Look at the page (Pro)
browser_lookDescribe or answer questions about the current page in text, including visible layout, images, charts, or broken elements, without sending an image.
Instructions
A vision model looks at the page and answers in text: describe it, or answer your question about what is visible (layout, images, charts, whether something looks broken). Costs you a few hundred tokens instead of an image, and works in clients that cannot show images. Deputy Pro.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "browser_look"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | No | ||
| question | No |