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

Annotations already cover readOnly/idempotent/non-destructive/openWorld, so the description's added value is the establishment-level geography semantics and the required-criterion rule — both meaningful behavioral context. It does not disclose pagination ceilings (page max 20, per_page max 10) or ranking/sorting behavior, which would matter for a broad search.

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?

Four sentences, front-loaded with the searchable keys, then constraint, then a semantic caveat, then return shape. Dense and largely waste-free, though the return-value sentence is partly redundant with the output schema.

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?

Covers the essentials for an 8-param search tool: at least one criterion, geo-filter scope, and what comes back. Gaps are pagination limits and result ordering, which an agent would want when narrowing broad searches.

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?

With 50% schema coverage, the description usefully explains that q accepts name, SIREN, SIRET, or director name and that the listed filters are optional. It adds little for page/per_page (undocumented in the schema) beyond implying paging exists, and doesn't mention the maximums.

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 ("Recherche des entreprises françaises") and enumerates the searchable keys (nom, SIREN, SIRET, dirigeant), which clearly separates it from the single-record sibling get_company. It never names a sibling or explicitly contrasts with get_company/search_places, so it falls short of the top tier.

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?

"Au moins un critère est requis" supplies a real gating rule the schema does not express (required is empty). "Les filtres géographiques portent sur un établissement quelconque, pas seulement sur le siège" tells the agent how to interpret results before calling. No explicit alternatives or when-not guidance is given.

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