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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Lecture seule' is redundant, but the description adds genuinely useful context: results are indicative and normative documents (ERP regulation, signed CCTP) take precedence. That reliability caveat is not available in any structured field.

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 tight paragraph, front-loaded with the call condition and the normative caveat at the end. The only inefficiency is restating the scene object shape twice, which duplicates the schema but costs little.

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 a single optional nested parameter, full schema description, and annotations covering the safety profile, the description supplies the missing pieces: what categories are verified and the authoritative-source caveat. No output schema exists, so an agent has no information on the verdict format, which is the one remaining gap.

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 the description's 'scene : cafeteria {ventilation, eclairage, mobilier, securite}' restates the schema text verbatim rather than adding structure, nesting or format detail. Baseline 3 applies since the schema does the heavy lifting and the description adds nothing new.

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 states a specific verb and resource ('VERIFIER LA CAFETERIA / salle de restauration') and enumerates exactly what is checked (ventilation, eclairage, mobilier, securite). This clearly separates it from generic siblings like cao_bim_eclairage or cao_bim_mobilier, though the adjacent cao_bim_cuisine is never named as a contrast.

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?

'Appelez quand vous devez VERIFIER LA CAFETERIA' states the trigger condition, and 'Indicatif — reglement ERP et CCTP signes priment' implies when its output should NOT be treated as authoritative. However, no sibling alternative is named and no exclusions (e.g. versus cuisine or salle_commune) are given.

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