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

Annotations already declare readOnlyHint/destructiveHint=false, so "Lecture seule" is redundant. The description does add genuinely new behavioral context: the result is indicative only and signed DTU 25.41 plus the acoustic note take precedence — a material caveat for how an agent should treat the output.

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-loads the trigger and the checks, then the scene shape, then the caveat. Dense but every clause carries a threshold, field name, or caveat; nothing is pure filler, though the packed parenthetical is heavy to parse.

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?

Inputs are well covered (scene structure, field meanings, thresholds), and the indicative caveat is present. However, with no output schema, the description never says what the check returns — per-check pass/fail, violations list, severity — leaving the agent to guess the response shape.

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 schema already names the cloisons fields, so baseline is 3. The description adds value by documenting the type enumeration (distributive|separative) which the schema does not, and by linking each field to the check it feeds (entraxe -> CL-OSSATURE, renfort -> CL-HAUTEUR).

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 CLOISONS SECHES", DTU 25.41) and enumerates the exact checks with thresholds (entraxe <= 600 mm, hauteur <= 3,5 m). Siblings like cao_bim_doublage or cao_bim_acoustique are not named, so the boundary is implied by the DTU reference rather than stated.

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..." gives a clear trigger condition, and the enumerated check IDs (CL-OSSATURE, CL-PLAQUES, CL-ISOLATION, CL-HAUTEUR) scope the job. No explicit when-not or alternative-tool routing is provided.

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