read_page
Retrieve the current page's URL, title, and indexed interactive elements to obtain valid indices for clicking or typing. Include visible body text with include_text when needed.
Instructions
[Real Chrome browser via the OctoLimb extension — drive the user's browser; use only when the task requires acting on a real website.] Read the current page in this task's tab: URL, title, and an indexed list of interactive elements. Call this before click_element, input_text, or the dropdown tools to get valid indices. Body text is omitted by default — pass include_text when you actually need to read page content, not just interact with it.
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": "read_page"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| include_text | No | Include the page's visible body text (default false — most steps only need element indices) | |
| max_text_length | No | Max characters of body text to return when include_text is true (default 4000) | |
| viewport_expansion | No | Expand the viewport by this many pixels when indexing elements (default 0 — only visible elements are indexed). Set to -1 to index all interactive elements on the page regardless of visibility. |