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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description is consistent with them while adding real context: the data is France-scoped public listings, and each result returns the listing address plus where to make contact and where to report a sighting. It does not cover pagination or how results are ordered, but it clearly exceeds what the annotations supply.

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?

Content is front-loaded: the resource scope, the statut hint and the return behavior all appear before the English mirror. The bilingual duplication doubles the length, but that mirrors the tool's own langue parameter and is therefore earned rather than wasteful.

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 10-parameter, zero-required search tool with no output schema, the description supplies the missing pieces an agent needs: geographic scope (commune or lat/long point), France-only coverage, and what a result contains. It omits pagination/limite behavior and how commune interacts with latitude/longitude when both are supplied, which keeps it short of complete.

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 80%, so the schema already documents most parameters (statut, commune, rayon, langue, jours, texte). The description adds one genuinely new semantic detail — keywords match race names in French or English — but the statut explanation largely restates the schema, so this sits at the high-coverage 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 gives a specific verb (cherche) and resource (annonces publiques de Mission Museaux) and enumerates the exact listing types covered: perdus, trouvés et recueillis, vus en liberté. This implicitly separates it from chercher_adoptions, but no sibling is named explicitly, so it stops short of full sibling differentiation.

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?

It hints at usage with 'Le statut « trouve_ou_errant » couvre ce qu'une personne qui a perdu son animal doit consulter', which tells an agent which filter a grieving owner should pick. However, there is no explicit when-to-use-this-vs-alternatives guidance (e.g. versus chercher_par_photo or voir_annonce), so usage remains implied rather than stated.

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