Skip to main content
Glama

browser_crawl

Open a real browser to analyze web pages, extract readable text, metadata, links, images, entities, and key sentences, then follow relevant links for OSINT reconnaissance.

Instructions

Open a real browser, analyze a page, then follow relevant links.

Extracts readable text, meta, links, images, entities and key sentences; follows up to 2 relevant links per page. Optional screenshots of the first pages. Use start_url as a URL or a comma-separated list of seed URLs.

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": {
      "start_url": "<start_url>"
    },
    "name": "browser_crawl"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNo
max_depthNo
max_pagesNo
start_urlYes
screenshotsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full load. It does disclose useful traits: a real browser is opened, links are followed 'up to 2 relevant links per page', and screenshots are optional and limited to first pages. It says nothing about runtime cost, blocking/auth behavior, JS requirements, or what the result set looks like, which are the gaps that matter for a crawling tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with the action front-loaded, followed by output contents and then the start_url convention. Minor redundancy between 'follow relevant links' and 'follows up to 2 relevant links per page', but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter, annotation-free tool with no output schema, the description covers the crawl behavior and the extracted data types reasonably but leaves query and max_pages opaque and gives no sense of result structure or ordering. It is callable but not confidently callable without guessing parameter behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for all five parameters. It explains only start_url (URL or comma-separated seed list) and effectively screenshots ('optional screenshots of the first pages'); query, max_depth, and max_pages are never mentioned, and 'up to 2 relevant links per page' sits ambiguously against the max_depth parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Open a real browser, analyze a page, then follow relevant links') and enumerates what is extracted, which distinguishes it from a plain open/extract tool. It does not name the sibling tools (browser_open, browser_extract) it is closest to, so differentiation is implied rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the mechanics: multi-page crawling with link following and screenshots of 'the first pages'. There is no explicit statement of when to prefer this over browser_open, browser_extract, or browser_screenshot, and no prerequisites or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.