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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Lecture seule' only restates them. The description does add real behavioral context beyond the annotations: results are 'Indicatif' and a signed CEKAL manufacturer datasheet prevails — a material caveat about how much authority to give the output. It stops short of describing the evaluation output format.

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 trigger and check list are front-loaded, and the caveat ('Indicatif — fiche fabricant CEKAL signee prime') is placed last where it matters most. It is a single dense run-on with heavy parentheses, which costs some 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?

For a one-parameter, read-only checker with no output schema, the description supplies the pass criteria, the VP-* rule labels that hint at the report's structure, and the caveat on authority. Only the return shape (per-rule compliance verdicts) is left implicit, which the VP codes largely telegraph.

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 'scene' parameter is already described as a vitrages array with the same field list, so the repetition alone earns no credit. However, the description adds semantics the schema lacks: what each field is judged against (sg <= 0,4, tl >= 0,5, uw thresholds for triple vs double) and that 'orientation' must be declared, which tells the agent how to populate and interpret the nested fields.

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?

Names a specific verb (VERIFIER) and resource (performances des vitrages / enveloppe), then enumerates the exact criteria checked (Sg <= 0,4 south/west, TL >= 0,5, Uw <= 1,1 triple / 1,6 double, orientation). This clearly separates it from the sibling cao_bim_vitrages (which manages glazing objects) — an agent knows this one evaluates rather than edits.

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?

Opens with an explicit trigger: 'Appelez quand vous devez VERIFIER LES PERFORMANCES DES VITRAGES'. It does not name a sibling alternative or a when-not-to-use case, but the trigger condition and the rule thresholds make the invocation context unambiguous.

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