Skip to main content
Glama

site_policies

Read-only

Fetch robots.txt, llms.txt, llms-full.txt, ai.txt and /.well-known/security.txt for up to 5 sites. Parses AI-crawler rules (GPTBot, ClaudeBot, Google-Extended, CCBot, PerplexityBot, …) and whether a given path is allowed, lists sitemap URLs, and parses security.txt contact/expiry. Price: 0.005 USDC per call (x402, Base).

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": {
      "urls": "<urls>"
    },
    "name": "site_policies"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoDefault path to test against robots.txt
urlsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the description focuses on what the agent would not otherwise know: the per-call price of 0.005 USDC charged via x402 on Base, and the concrete set of files retrieved and parsed. It stops short of describing failure behavior — e.g. what is returned when a site lacks robots.txt or is unreachable — which matters for an open-world fetch.

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?

Two dense sentences, front-loaded with the fetched resources and then the derived outputs. Every clause carries information, though the long parenthetical bot list adds length without much decision value and the pricing note is tacked on at the end.

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, so the description correctly spends its budget describing return content (per-crawler rules, path-allowed verdict, sitemap URLs, security.txt contact/expiry) and the payment model. What is missing is per-URL result structure and behavior for missing or blocked files, which an agent needs to interpret partial results.

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 coverage is 50%, with the urls array undocumented in the schema; the description compensates by saying 'for up to 5 sites' (matching maxItems=5) and by explaining that the path is tested for allowance against robots.txt, which clarifies the otherwise opaque path property. It does not explain the top-level path vs. per-URL path object precedence, leaving one genuine ambiguity.

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

Purpose5/5

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

States a concrete verb (Fetch) plus the exact resources (robots.txt, llms.txt, llms-full.txt, ai.txt, security.txt) and the scope limit (up to 5 sites). It also names what is computed from those files, so an agent can tell instantly this is a policy/crawler-rules reader rather than a link or header checker.

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?

The listed capabilities (AI-crawler rules, path-allowed checks, sitemaps, security.txt contacts) imply when the tool is appropriate, but there is no explicit 'use this when…' clause, no exclusions, and no reference to the sibling tools for overlapping needs such as check_headers. Usage is inferable rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources