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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so safety is partly covered. The description adds genuinely useful behavior: the audit is free, capped at 200 pages, covers four named dimensions, and returns an identifier rather than results — signalling an asynchronous job pattern. It stops short of stating expected duration or whether repeated calls create duplicate audits, which matters given idempotentHint=false.

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?

One dense sentence that front-loads the action, then the scope, then the dimensions, then the return value. No filler and nothing repeated from the title.

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 compensates by explaining that the return value is an identifier to feed into resultat_audit. Combined with the scope and dimension list, an agent has enough to call it correctly; only timing/asynchrony details are left implicit.

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?

There is a single parameter with 100% schema description coverage, so the schema already explains 'adresse' with an example. The description adds only the constraint that the site must be public, which is meaningful but marginal. Baseline 3 applies 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 and resource ('Lance l'audit ... d'un site public'), names the four audit dimensions covered (SEO Google, AI visibility, accessibility, technical) and the 200-page scope. It also distinguishes itself from the sibling by stating it returns an identifier to hand to resultat_audit, so an agent can tell it apart from the results-reading tool.

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?

Implies the workflow clearly: use this to start an audit, then pass the returned identifier to resultat_audit. It also constrains inputs to public sites. It does not state when not to use it (e.g. private/authenticated sites, already-audited sites, or rate limits on repeated free audits), so a small gap remains.

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