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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, so "Lecture seule" adds nothing. What does add value is the disclaimer "Indicatif — DTU 26.2 signe prime", which tells the agent these verdicts are advisory and may be overridden by the signed standard — a behavioral trait annotations cannot express. It also exposes the rule identifiers the check produces.

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 call trigger and the four rule codes with their thresholds, all of which earn their place. The trailing "scene : chapes [...]" block duplicates the schema description verbatim and could be dropped, and no wasted framing otherwise.

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 rule-checking tool with no output schema, the description supplies the input shape, the applicable thresholds, and the caveat about normative precedence, and the CH-* codes imply a per-rule result taxonomy. It never states the actual return format (per-rule pass/fail, list of non-conformities, missing-data behavior), which is the 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 description coverage is 100% and the single `scene` parameter is already documented field-by-field, so the baseline is 3. The description restates the same nested shape (nom, epaisseur_mm, isolation_res_m2k_w, bande_peripherique, joints_fractionnement, surface_m2) without adding units, defaults, or tolerances beyond it.

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 (VERIFIER) and resource (CHAPES FLOTTANTES), scoped to second oeuvre / DTU 26.2, and enumerates the four exact checks with thresholds. That is far more specific than the generic cao_bim_* siblings, so an agent can separate it from e.g. cao_bim_planchers or cao_bim_etancheite without reading the schema.

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 CHAPES FLOTTANTES" gives an explicit trigger condition and the regulatory context. There is no statement of when NOT to use it and no named alternative (e.g. cao_bim_dtu or the generic cao_bim_verifier), so it stops short of full routing guidance.

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