Skip to main content
Glama

crawl

Extract pages from a site starting at a URL and return them as Markdown, following links breadth-first within depth, page, and domain limits while listing skipped URLs with reasons.

Instructions

Crawl a site starting at url and return each page as Markdown.

Follows links breadth-first up to max_depth link hops (limit 5) and max_pages pages (limit 100). same_domain=True stays on the starting host. Skipped URLs (robots.txt, blocked, errors) are listed with the reason. Long crawls stop at a time/size budget and return the pages collected so far.

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": "crawl"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
max_depthNo
max_pagesNo
render_jsNo
same_domainNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses breadth-first traversal order, hard caps (depth 5, pages 100), host confinement via same_domain, robots.txt/blocked/error handling with reasons, and truncation at a time/size budget returning partial results. It stops short of stating rate limits, auth needs, or whether failures raise versus being reported, which keeps it from a 5.

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

Conciseness5/5

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

Four short sentences, front-loaded with the core action, then traversal semantics, then limits, then edge-case handling. Every sentence adds information and nothing is repeated from the name.

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

Completeness4/5

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

There is no output schema, and the description does explain what comes back (Markdown pages plus a list of skipped URLs with reasons) and how long crawls terminate. That covers nearly everything an agent needs, with render_js and error-raising semantics being the only real gaps.

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

Parameters4/5

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

Schema description coverage is 0%, so the description has to compensate and largely does: it defines max_depth as link hops with a cap of 5, max_pages with a cap of 100, and same_domain as staying on the starting host. The fifth parameter, render_js, is never mentioned, leaving one behaviorally significant option undocumented in both places.

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 opens with a specific verb and resource ('Crawl a site starting at url') and names the return artifact ('each page as Markdown'), so the agent knows exactly what the tool produces. It does not explicitly contrast itself with the sibling 'scrape' or 'map', which would be needed for a 5.

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 through the 'starting at url' framing and the depth/page limits, but there is no explicit when-to-use vs when-not statement and no pointer to 'scrape' for single pages or 'map' for URL discovery. An agent can infer intent but gets no routing guidance.

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