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

Beyond the readOnly/destructive annotations it adds real behavior: validity windows (DTA 6 years, CREP to be refreshed if lead found more than a year ago), the requirement for a certified diagnostician, and the caveat that results are indicative with certified reports taking precedence. The 'Lecture seule' clause merely restates readOnlyHint, but the reliability disclaimer is a genuine addition.

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 trigger condition, then the diagnostic rules, then the input shape, then the disclaimer. Dense but every clause carries domain information; the all-caps emphasis is a style choice rather than wasted text.

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?

Covers the input shape and the caveats well, but there is no output schema and the description never indicates what comes back (which diagnostics are missing, expired, or compliant). For a verification tool the agent must infer the response form, which is a visible 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?

With 100% schema coverage the baseline is 3, but the description goes further by enumerating the nested scene fields (annee_construction, travaux_prevus, zone_termites, diagnostics with amiante/plomb/termites sub-keys) and by tying each field to the rule it drives. That adds interpretive value for a nested object the schema only names.

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+resource: verifying mandatory pre-works diagnostics (asbestos DTA, lead CREP, termite survey). The three diagnostic families are named concretely, so an agent cannot confuse it with generic cao_bim_* model tools. However no sibling is named as a contrast point, so it lands just short of 5.

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 invocation trigger ('Appelez quand vous devez verifier... AVANT TRAVAUX') and gives the legal thresholds that select each check (building before 1997 for asbestos, before 1949 for lead, regulated termite zones). No when-not-to-use condition or alternative tool is mentioned.

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