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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so 'Lecture seule' adds nothing. The genuinely useful addition is that the output is indicative and subordinate to Eurocode 5 and signed CCTP documents. However, with no output schema, the description never says what the check returns (findings list? per-facet verdicts? behaviour when the scene contains no trusses), leaving a real gap.

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?

Front-loaded with the invocation trigger, then the facet enumeration, then the precedence caveat — no filler. The uppercase emphasis and repeated key list make it slightly denser than necessary, but every clause carries information.

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 single-parameter, read-only inspection tool whose safety profile is fully covered by annotations and whose parameter is fully documented by the schema, the description supplies the trigger, the scope of the four checks, and the normative caveat. Only the shape of the returned findings is unaddressed, which is a minor omission here.

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 single nested 'scene' parameter is already documented as 'fermes {composition, assemblage, appuis, protection}'; the description repeats exactly that structure. The FE-COMPOSITION/FE-ASSEMBLAGE/FE-APPUIS/FE-PROTECTION mapping does add a little meaning about what each sub-key is evaluated against, but no format or required-shape guidance 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 ('VERIFIER LES FERMES de charpente') and enumerates the four checked facets (composition, assemblage, appuis, protection) with their codes, so the agent knows exactly what is inspected. It does not distinguish itself from near-neighbours in the enormous cao_bim_* family (charpente, chevrons, pannes, ossature_bois), so sibling differentiation stays implicit.

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 LES FERMES' gives an explicit invocation trigger, and 'Indicatif — Eurocode 5 et CCTP signes priment' sets the boundary that signed contractual documents override the result. No when-not condition or named alternative tool is given, which keeps it below a 5.

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