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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description reinforces this with 'Lecture seule'. More valuable is the caveat 'Indicatif — DTU et CCTP signes priment', which tells the agent that findings are non-authoritative and contractual documents override them — context the annotations cannot express.

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 condition is front-loaded, the four check axes follow compactly with stable CO-* codes, and the disclaimer closes the sentence. Dense but every clause carries information; no filler.

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?

One optional nested parameter, annotations covering the read-only profile, and no output schema mean the description only needs to convey intent and caveats, which it does. The remaining gap is that it never hints at what the check returns (per-axis verdicts? list of anomalies?), which matters for a verification tool.

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 one parameter and 100% schema description coverage, the schema already documents `scene` as a CAO scene containing corniche {fixation, etancheite, protection, materiau}. The description restates that structure verbatim without adding expected value types, granularity or accepted sub-keys, so it neither compensates nor detracts.

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 states a specific verb (VERIFIER) and resource (LA CORNICHE) and enumerates the four axes checked (fixation/ancrage, etancheite, debord/protection, materiau/finition), so the tool's job is unambiguous. It does not, however, differentiate itself from adjacent siblings such as cao_bim_bandeaux, cao_bim_acroteres or cao_bim_cheneaux_gouttieres, which an agent could easily confuse with a cornice check.

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 LA CORNICHE' gives an explicit trigger condition, which is more than nothing. But there is no when-not guidance and no named alternative for neighbouring envelope elements, so the routing decision against the many similar cao_bim_* inspection tools is left to inference.

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