Read a web page as clean Markdown (with token count)
read_pageFetch a public URL and return its main content as clean Markdown (navigation, scripts, footers removed; links absolutized), plus title, final URL and an estimated token count, truncated to max_tokens. Cheaper on context than raw HTML.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "read_page"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| max_tokens | No | Truncate output to about this many tokens (default 8000, max 50000) | |
| include_links | No | Keep [text](url) links (default true) |