Start an audit (non-blocking)

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

With no annotations present, the description carries the full burden. It usefully discloses the async/non-blocking behavior and that the response contains an id and status. It does not mention permission/auth requirements, rate limits, cost, or crawl constraints, which leaves meaningful behavioral gaps for a tool that launches a crawling job.

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 short sentences with zero filler; the non-blocking behavior and return value are front-loaded before the routing hints. Every 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?

No output schema exists, and the description partially compensates by naming the return payload (id, statut). For a job-launching tool with no annotations, the async contract and follow-up path are covered, though callers get no guidance on permissions or failure modes.

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?

Schema description coverage is 100%, so the schema itself documents url, siteId and maxPages adequately. The description only restates the URL ('sur une URL') and adds no format, default, or bounds detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb (Démarre/Starts) and resource (audit SEO & GEO sur une URL), plus the key modifier 'sans attendre' that separates it from the sibling audit_and_wait. An agent can tell it apart from both the blocking variant and the read-only status tools 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.

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

Explicitly routes follow-up work: 'Utilisez get_audit_status pour suivre, get_audit pour les résultats.' That is clear when-to-use guidance for the downstream calls. It does not, however, state when to prefer this over audit_and_wait, so the alternative selection is left to inference from 'sans attendre'.

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