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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so "Lecture seule" is redundant. The genuine added value is "Indicatif — DTU plomberie et CCTP signes priment", which tells the agent the output is non-normative and must yield to signed DTU/CCTP documents — a reliability caveat not expressible in annotations.

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 is front-loaded and the whole definition is three compact clauses with no filler. The only waste is that the four sub-check names are listed twice — once as codes and once as the scene object structure.

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 zero-required-parameter, read-only inspection tool with no output schema, the description covers the trigger, the scope of checks, and the caveat on result authority. It does not describe the shape of the check results, but the "indicatif" framing sufficiently sets expectations.

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%, so the baseline applies. The description restates the nested scene shape {robinetterie, evacuation, fixation, accessibilite} but adds no syntax, nesting or format details beyond what the schema already conveys.

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?

The description names a specific verb (VERIFIER) and resource (l'evier / bac de cuisine) and enumerates the four sub-checks with their codes (EV-ROBINETTERIE, EV-EVACUATION, EV-FIXATION, EV-ACCESSIBILITE). That is far more specific than most cao_bim_* siblings, though it never explicitly tells the agent how it differs from cao_bim_robinetterie, cao_bim_evacuation or cao_bim_cuisine, which cover overlapping ground.

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 L'EVIER" gives an explicit trigger condition, and the precedence note ("DTU plomberie et CCTP signes priment") implies the result is advisory only. However, there is no when-not guidance and no routing to the numerous overlapping siblings, so the agent must infer when this aggregated sink check is preferable to a single-component tool.

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