Skip to main content
Glama

Outil.io

Audit SEO

audit_seo
Idempotent

AUDIT SEO ET PERFORMANCE COMPLET d’un site, sur n’importe quelle URL publique (site Outil, prospect, concurrent). Explore jusqu’à maxPages pages (liens + sitemap, robots.txt respecté) et contrôle ~70 points : indexation (robots, sitemap, noindex, canonical, soft 404, pages orphelines/profondes), balises title/description (absentes, longueur, doublons), contenu (maigre, dupliqué), structure Hn (H1 absent/multiple), liens cassés internes/externes et redirections, images (alt, dimensions, lazy, format), HTTPS (redirection, HSTS, contenu mixte, www), mobile (viewport), données structurées JSON-LD, Open Graph/Twitter, langue/hreflang ; puis PageSpeed Insights mobile+ordinateur (Lighthouse + Core Web Vitals des visiteurs réels LCP/INP/CLS) sur l’accueil et 2 pages clés ; puis Google Search Console si le compte est connecté (clics, impressions, positions, requêtes à potentiel). Asynchrone (1 à 6 min) : suivre avec get_seo_audit. requestId stable = pas de doublon.

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": "audit_seo"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
maxPagesNo
pageSpeedNo
requestIdNo
searchConsoleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (openWorldHint, idempotentHint, non-destructive), the description discloses long-running asynchronous behavior with a concrete 1-6 minute window, the required follow-up tool, and the deduplication semantics of a stable requestId. It also states that robots.txt is respected during crawling, which is exactly the kind of behavioral context annotations cannot carry.

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?

The longest and most important facts are front-loaded in the opening clause, and each subsequent sentence lists concrete checks rather than filler. It is nevertheless a single dense block whose semicolon-chained enumeration is harder to scan than short structured sentences would be.

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 complex asynchronous crawler with five parameters and no output schema, the definition covers initiation, duration, follow-up retrieval, and deduplication. The remaining gap is the return payload itself: apart from implying a requestId, it does not say what the agent receives from this call versus get_seo_audit.

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 must compensate, and it largely does: maxPages is tied to crawl depth, pageSpeed to the PageSpeed Insights checks, searchConsole to the connected account, and requestId to duplicate protection over url. It still omits defaults and valid ranges (e.g. the 1-300 maxPages bounds), leaving some gaps the schema alone cannot fill.

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?

The description opens with a specific verb and resource: a complete SEO and performance audit of any public URL, and names the target audiences (own site, prospect, competitor). It also enumerates the exact scope of the audit (~70 checkpoints, PageSpeed, Search Console), which lets an agent separate it from sibling tools like get_seo_audit.

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

Usage Guidelines4/5

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

It clearly signals the usage context (any public URL, own/prospect/competitor site) and the crucial follow-up path: the run is asynchronous, takes 1-6 minutes, and should be tracked with get_seo_audit. What it does not do is explicitly exclude other alternatives such as audit_site_content or get_site_seo, so the choice between siblings is only partly guided.

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.