aeo_reportRenvoie le détail complet d’un audit existant (par audit_id) : score global, scores par catégorie et tous les critères (score + recommandation). Gratuit.
| Name | Required | Description | Default |
|---|---|---|---|
| audit_id | Yes | id de l’audit (renvoyé par aeo_audit) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already include readOnlyHint: true, and the description reinforces this by saying 'returns' and adding 'Gratuit' (free). It also discloses the exact content of the response (overall score, category scores, criteria). This adds context beyond the annotations without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that lists the resource, parameters, and return contents, plus a one-word note ('Gratuit'). Every word earns its place, with no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple getter with one parameter and no output schema, the description is complete: it states the input (audit_id) and the output structure (scores, criteria). It doesn't address error cases (e.g., audit not found), but that's not critical for this simplicity. The readOnlyHint annotation further completes the picture.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already has 100% coverage with a good description of audit_id, including where it comes from (returned by aeo_audit). The tool description merely says 'par audit_id' and adds no additional semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns the full details of an existing audit, including global score, category scores, and all criteria with recommendations. This specific verb+resource+scope distinguishes it from related tools like aeo_audit (which likely creates audits) and aeo_audit_status (which likely returns only status).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'audit existant (par audit_id)' makes it clear that this tool is for retrieving details of an already completed audit, implying you should first use aeo_audit to get an audit_id. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes within two domains (Google Ads and AEO), but some overlap exists (e.g., ads_pause_keyword vs ads_keywords, aeo_audit vs aeo_batch_audit). However, descriptions and parameter differences suffice to disambiguate.
Tools follow a consistent pattern: prefix (ads_ or aeo_) + verb + noun (e.g., ads_add_keywords, aeo_audit). Minor deviations like ads_ad_status (verb missing) and aeo_apply (verb only) are rare but present.
36 tools is on the high side, especially since there are two distinct service domains (Ads and AEO). While each tool has a specific function, the count feels slightly heavy for a single MCP server, bordering on too many.
The Google Ads toolset covers campaign management, keyword optimization, audience targeting, and performance analysis thoroughly. The AEO side covers audit, improvement generation, application, and monitoring. Minor gaps exist (e.g., no tool for ad creation beyond status changes), but overall the surface is comprehensive.