Skip to main content
Glama

Check whether pages can be found

audit_seo
Read-only

Audits HTML pages for SEO issues—titles, meta descriptions, canonicals, headings, alt text, Open Graph, JSON-LD—and reports errors and warnings, including cross-page duplicate or off-site URL checks.

Instructions

Reads HTML pages for what decides whether anyone finds them — title, meta description, canonical, lang, viewport, Open Graph, one , alt text, JSON-LD — WITHOUT touching any workspace. This is the server's audit, so it is the authority: the note attached to write_file is a local subset of the same rules. Pass baseUrl — the domain's own baseUrl from list_domains (e.g. https://marceau.qu4zr.com/), the same base the pages' canonicals use — to also get the checks a single page cannot make about itself — a canonical pointing outside the site, a hand-written sitemap listing URLs it does not own. Auditing several pages at once adds the cross-page ones: two pages sharing a title or a description. Returns { ready, checkedPages, errors, warnings, findings[] } where each finding has a stable code. ready means no error-level findings — warnings are advice, not breakage. Read it after building a site, and re-run it after fixing.

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": {
      "files": "<files>"
    },
    "name": "audit_seo"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoHow much to report about the HTML pages being written: "full" (default) everything, "minimal" only what an indexed page cannot do without, "none" to say nothing. Never blocks the write; a page with <meta name="robots" content="noindex"> is exempt either way.
filesYesThe files to read. Only whole HTML pages are audited — fragments, stylesheets and scripts are skipped and reported in checkedPages. Send every page of the site together to get the cross-page checks.
baseUrlNoWhere the site is published, e.g. "https://api.qu4zr.io/marceau/". Optional, and it unlocks the checks a page cannot make about itself: a canonical pointing outside the site, a sitemap listing URLs it does not own.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, and the description is consistent, reinforcing it with "WITHOUT touching any workspace." It adds real context beyond annotations: the server audit is authoritative, write_file's note is a local subset, and `ready` means no error-level findings while warnings are advice. However, it does not cover rate limits, auth, or failure modes, so with annotations carrying the safety profile a 3 is appropriate.

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-loads the core purpose and keeps every sentence earning its place, but the em-dash-heavy phrasing and long clauses make it denser than necessary. Still well-structured and free of filler.

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

Completeness5/5

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

No output schema exists, yet the description spells out the return shape ({ ready, checkedPages, errors, warnings, findings[] }) and the meaning of `ready` and stable `code`. Combined with the usage and parameter guidance, an agent has everything needed to call it correctly.

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?

Schema coverage is 100%, so the schema already documents all three parameters, making 3 the baseline. The description adds some meaning, notably that baseUrl should be the domain's own baseUrl from list_domains and match the base canonicals use, and that files should be sent together for cross-page checks, but it largely restates schema intent.

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 ("Reads HTML pages") plus the exact signals it inspects, and explicitly distinguishes itself from the write_file note ("a local subset of the same rules"). An agent can tell what this does and how it differs from the sibling without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use ("Read it after building a site, and re-run it after fixing"), a conditional for baseUrl ("to also get the checks a single page cannot make about itself"), and a batching rule ("Send every page of the site together to get the cross-page checks"). No inference required.

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