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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the description correctly focuses on what they cannot convey: the output is plain text, brands are returned in the requested order, and a missing brand is flagged without aborting the other results. It also confirms no account or key is needed.

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?

It is a single dense paragraph with zero filler, front-loading the action and scope before the return format and the sibling routing. The nested clause listing the fiche fields is long but each element is informative.

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?

With no output schema, the description fully carries the burden of return-value documentation by enumerating the fields of each fiche and the partial-failure behavior. Nothing an agent needs to call it correctly or interpret the result is missing.

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 coverage is 100%, so the array bounds, item type and case-insensitivity are already documented in the schema. The description adds only that output ordering follows input ordering, which is useful but thin beyond the baseline.

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 opens with a specific verb and resource ('Compare côte à côte 2 à 5 marques de l’annuaire') and immediately anchors scope with a concrete example. It also states the exact return shape (the same fiche as detail_offre), which separates it cleanly from every sibling.

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 routing is given for both adjacent needs: use detail_offre for a single brand, and rechercher_offres or offres_par_categorie to find brands worth comparing. The agent never has to infer which tool fits.

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