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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine value by disclosing that results are pre-validated and not AI-generated, but says nothing about what happens on no-match queries, result volume, or freshness of the answers.

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?

Two short sentences, no filler, with the salient qualifier ('sans génération IA') placed last for emphasis. Nothing could be removed without losing information.

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 one-parameter read-only search with no output schema and full annotation coverage, the description is nearly sufficient, but it omits what a returned 'validated answer' looks like, how sources are cited, and how the tool behaves when no validated answer exists.

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 0% and the single 'query' parameter carries only a maxLength constraint. The description indirectly scopes what the query should be about ('services, forfaits et modalités d'Effset') but gives no guidance on phrasing, language, or format for the 600-character query.

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 names a specific verb ('Trouver') and resource domain (services, forfaits, modalités d'Effset), and adds the key qualifier 'réponses validées' plus 'sans génération IA' — enough for an agent to know this is a validated-fact lookup, not a generative chat. The bare tool name 'ask' would be ambiguous without it, and there are no siblings to confuse it with.

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?

'Recherche sans génération IA' implies the usage context (factual lookup rather than synthesized answers) but states no explicit when-to-use or when-not-to-use rule, no prerequisites, and lists no alternatives — there are no siblings, so no routing information is supplied.

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