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

Annotations already declare readOnlyHint/destructiveHint=false, so 'Lecture seule' is redundant confirmation rather than new information. The description does add genuine behavioral value by disclosing the output contract: each discrepancy is returned with its norm, its article, and the corrective action.

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?

A single front-loaded sentence: trigger first, scope enumeration second, return contract and read-only note last. The norm enumeration is long but each reference earns its place by defining scope; nothing is padding.

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?

With no output schema, the description correctly compensates by describing what is returned per violation. For a single-parameter read-only checker, the only real gap is the missing differentiation from sibling conformity tools.

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?

Only one parameter exists and schema description coverage is 100%, with the nested scene object already listing its constituents (murs, ouvertures, toitures, pieces, ventilation, evacuations, escaliers, garde_corps). The description's domain list loosely hints at what the scene must contain, but adds no structural or formatting guidance beyond the schema, so the baseline 3 applies.

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 la conformite d'une scene aux normes d'execution francaises (DTU)') and then enumerates the exact domains covered with their norm references (DTU 20.1, 36.5, NF P01-012, 40.35, 60.11, 68.3). This is far more specific than the many sibling 'cao_bim_*' verification tools and lets an agent recognize the DTU-compliance scope immediately.

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 an explicit trigger condition, and the enumerated norms implicitly bound the scope (execution/DTU, not accessibility, fire, or acoustics). However, it never names or excludes the closest alternatives (cao_bim_conformite, cao_verifier, cao_bim_reglementations), leaving the agent to infer the boundary itself.

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