Skip to main content
Glama

SEO Rank Fixer

Site audit

site_audit
Read-onlyIdempotent

The latest Site Audit of one site (our own crawl of its pages): health score out of 100 and its trend, counts of errors, warnings and notices, what is new or fixed since the last crawl, and the problems most worth fixing first (ranked by severity, pages affected and the Google clicks of those pages), each with why it matters, how to fix it and example URLs. Read-only: it never starts a crawl.

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": {
      "siteId": "<siteId>"
    },
    "name": "site_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteIdYesA site id from list_sites.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotent, and the description reinforces this with the meaningful nuance 'it never starts a crawl', telling the agent the data is pre-existing rather than freshly generated. It also discloses the ranking logic for problems (severity, pages affected, clicks) and per-item payload (why it matters, how to fix, example URLs), which fills the gap left by the absent output schema. It omits the edge case of a site with no audit yet.

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?

Front-loaded with the core identity, then the return contents, closing with the read-only caveat. It is one dense sentence that could be split for readability, but essentially every clause carries information an agent needs.

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?

For a single-parameter read tool with no output schema, enumerating the return payload and its ranking criteria is exactly the needed information, and the annotations cover the safety profile. Slight gap: no statement about what happens when a site has never been crawled or how stale the 'latest' audit may be.

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

Parameters3/5

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

With one parameter at 100% schema description coverage, the schema already defines siteId, its UUID format and that it comes from list_sites. The description adds no further meaning about the parameter, so baseline 3 applies.

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 specific verb and resource: 'The latest Site Audit of one site (our own crawl of its pages)'. It then enumerates the exact contents (health score, trend, error/warning/notice counts, new/fixed, ranked problems), so an agent knows precisely what it gets and can distinguish it from Google-data siblings like site_performance.

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 return contents (diagnose a site, find what to fix first), but the description never says when to pick this over overlapping siblings such as top_fixes, opportunities, site_performance or index_status. No exclusions or prerequisites are given.

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.