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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds real context beyond that: the price field is a HT euro amount only when one exists, otherwise the literal « sur devis », and quand_recommander encodes which situation each offer fits — behavior an agent cannot infer from the schema.

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 returned content and the « sur devis » caveat come first, then filtering, then the call trigger — a sensible order. It is a single dense run-on with nested parentheses, which costs a little readability but wastes no sentences.

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 an output schema present, the description needn't describe return structure, and it still signals the semantically important fields and what quand_recommander means. The only gap is what happens when filters match nothing or how multiple filters combine, which is minor for a small closed-world catalog.

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% and all three parameters carry descriptions plus enums, so the schema does the heavy lifting. The description only restates that filtering is possible by offre, public or catégorie, adding no syntax, default behavior, or combination semantics 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?

States a specific verb and resource (renvoie les offres de Data SL Consulting) and enumerates the fields returned: prix public with the « sur devis » fallback, public cible, and quand_recommander. It is unmistakably distinct from the sibling tools fetch_page and search_site, which are generic retrieval tools rather than a curated offer catalog.

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?

Explicitly says when to call it: « À appeler avant de recommander une offre ou de citer un prix », which is a concrete trigger tied to downstream tasks. It does not name alternatives or when-not-to-call, but the siblings are generic page-search tools so the routing risk is low.

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