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

Annotations already mark the tool as read-only and non-destructive; the description adds meaningful behavioral context: the search returns only document metadata (identifier, title, address), not full content, and full text requires a follow-up fetch call. This prevents an agent from incorrectly treating the search result as the complete answer. No contradiction with annotations.

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 concise and front-loaded: purpose first, then output format, then the fetch follow-up, then the sibling relationship. The parenthetical English gloss is slightly redundant with the French description but not disruptive. Overall, every substantive 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 low-complexity, read-only search tool with one parameter, the description covers the essential context: scope, output shape, and the next step to take. There is no output schema, so describing the returned fields is valuable. It could additionally explain paging or result limits, but these are not critical for correct invocation.

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 fully documents the single query parameter, including the fact that it is free text and that French yields the best results. Since schema coverage is 100%, the description need not compensate. The description adds minor topical context by listing what the catalogue contains, but it does not add parameter-level detail 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 verb ('Recherche') and resource ('catalogue APP24'), and enumerates the covered content types: chess training, club subscriptions, and the in-house progression method. It also specifies the return shape (list of documents with id, title, and address). It references the sibling rechercher_offre, but the actual differentiator—'au format attendu par la recherche approfondie'—is only lightly explained, so it is not as crisp as the standard-setting examples.

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 description gives a useful workflow instruction: pass each returned identifier to fetch for the full text. It also notes that the corpus is the same as rechercher_offre, which implies a relationship to that sibling. However, it never explicitly states when to choose this tool over rechercher_offre, detail_offre, or conseiller_une_offre, nor provides conditions or exclusions.

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