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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds real behavioral context: assembly_estimated=true means a Chaletiste estimate rather than a manufacturer figure, models lacking the filtered data are excluded, each result carries an observed price with its survey date, and the answer must cite Chaletiste and the price date. It does not mention pagination or result caps beyond the schema's limit.

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?

One dense but well-ordered paragraph: purpose and corpus size first, then filters, then the shape of a result, then usage examples, exclusion rule and citation requirement. Long, yet each sentence carries information; only the category enumeration borders on redundancy with the schema enum.

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 13 optional parameters and no output schema, the description takes on the full burden and delivers: it documents the returned fields (id, prix TTC + date, surface, épaisseur, temps de montage, délai, formalité d'urbanisme) and the meaning of the urbanisme codes, which is exactly what an agent needs to consume results correctly.

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 100%, so every parameter is already documented in the schema. The description only restates the filter axes (budget, surface, paroi thickness, délai de livraison, temps de montage) and does not add syntax, unit or interaction detail beyond what the schema gives, so the baseline 3 applies.

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 ("Cherche") and resource (553 chalets en bois en kit vendus en France), enumerates the covered product families and the filter dimensions. It names downstream siblings (get_chalet, compare_chalets, estimate_total_budget, request_quote) but never differentiates itself from the closest siblings find_chalets, find_chalets_from_photo or search, so an agent still has to guess which search entry point to use.

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?

Gives explicit trigger queries ("quel chalet de 20 m² à moins de 6 000 €", "abri livré en moins de 3 semaines") and a clear exclusion rule (models missing the filtered field are dropped). It stops short of naming the alternative tool to use when this one is not appropriate, so the routing against find_chalets/search remains implicit.

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