Skip to main content
Glama

Outil.io

Audit site content

audit_site_content
Read-only

AUDIT DU SITE ENTIER EN UN APPEL (remplace get_page_structure + get_page_elements page par page). Pour toutes les pages, en parallèle : snapshot, chaque texte modifiable (titres, paragraphes, boutons, menus, formulaires, pieds de page, alt) et chaque lien, adressés par le chemin exact à écrire (@ref.content, @ref.custom.donnees.links.0.label…). sharedTexts regroupe les textes répétés sur plusieurs pages ; flags signale le contenu de démonstration (lorem ipsum, example.com, 555…) et les textes probablement en anglais. Enchaîner directement sur apply_site_changes, sans autre lecture.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_site_content"
  }
}

Input Schema

NameRequiredDescriptionDefault
linksNo
offsetNo
pageIdsNo
textOffsetNoAvec un seul pageId : reprendre ses textes à cet index (nextTextOffset)
maxTextLengthNo

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=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds substantial value beyond that: parallel fan-out over all pages, the returned payload (snapshot, editable texts, links, alt text), the '@ref.content'-style addressing scheme, plus sharedTexts deduplication and quality flags for lorem ipsum/example.com/probable-English copy. It stops short of describing pagination or volume limits.

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 key claim is front-loaded in capitals, then the payload contents are enumerated compactly with semicolons, ending on the prescribed next action. Dense but every clause carries information; a slight cost is the run-on middle sentence mixing return shape, deduplication and flags.

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

Completeness3/5

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

With no output schema, the description does useful work sketching the response, which is the right priority for a read tool. However, four of five input parameters (including the pagination controls that matter at maxItems 200) remain unexplained, so an agent calling it repeatedly lacks the context to page correctly.

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

Parameters2/5

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

Schema description coverage is only 20%, so the description needed to carry parameter meaning and does not: links, offset, pageIds and maxTextLength are never mentioned, nor is the interaction between pageIds and textOffset. Only 'Pour toutes les pages' implicitly hints at the default page scope; the paginated resume/limit behavior is left entirely to the agent's reading of the schema.

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 scope — 'AUDIT DU SITE ENTIER EN UN APPEL' — and explicitly names the two siblings it supersedes ('remplace get_page_structure + get_page_elements page par page'). An agent can distinguish it from the per-page readers without opening any 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?

It states both the replacement condition (whole-site audit instead of page-by-page element reads) and an explicit do-not-do instruction: 'Enchaîner directement sur apply_site_changes, sans autre lecture', which forbids redundant read calls after the audit. The follow-up step is also named, leaving little to inference.

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.