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

The description goes far beyond the annotations, revealing the asynchronous behavior (~2 min), the cost (50 GTO debited at completion), and a concurrency constraint (do not relaunch while running). Annotations only provide basic safety hints (readOnlyHint=false, destructiveHint=false), so this rich behavioral context is valuable and not contradictory.

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?

Three sentences, all dense with information: the action, the asynchronous/cost/concurrency caveats, and the follow-up workflow. No fluff or redundancy; each sentence earns its place.

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 tool that initiates an async audit, the description covers essential context: what it returns (audit_id), how to track progress (status), how to get results (report/improvements), cost, and concurrency warnings. No output schema exists, but the immediate return value is clearly stated, making this sufficiently complete.

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 schema already covers the single parameter 'url' with a description ('URL ou domaine à auditer') at 100% coverage. The tool description restates 'URL' but adds no new meaning beyond the schema, so it meets the baseline but does not exceed it.

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 specific action ('Lance un audit AEO/GEO d'une URL') and the immediate output (audit_id). It distinguishes from siblings by detailing the asynchronous nature (~2 min) and the follow-up workflow (aeo_audit_status, aeo_report / aeo_improvements), making it unmistakable from related tools like aeo_batch_audit or aeo_audit_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?

Explicit workflow guidance is provided: 'Suivre avec aeo_audit_status jusqu'à completed, puis aeo_report / aeo_improvements'. It also includes a clear exclusion: 'NE PAS relancer le même audit pendant qu'un run est en cours', and implicitly guides when not to use this tool by naming the status/report tools as next steps.

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