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

Annotations already declare readOnlyHint=true and openWorldHint=false, so 'Lecture seule' is redundant. The description does add real content about behavior: what gets computed in dossier mode (DTU, sismique, cout/planning/courbe en S, note a signer) and that a consolidated verdict is produced. It says nothing about prerequisites on scene, failure modes, or cost of the full dossier call.

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 an explicit 'Appelez quand...' trigger and kept to a single dense sentence using dashes to enumerate outputs. Slightly long and title-like in its first clause, but no filler sentences.

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 13 parameters, nested objects and no output schema, the description does the necessary work of enumerating what each mode returns (regulation, bilan, gate, deliverables; or the full dossier with consolidated verdict) so the agent can judge output value. The remaining gap is the unresolved overlap with cao_bim_dossier_complet and no mention of how scene is consumed.

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%, so the baseline is 3. The description adds meaning beyond the schema by framing action=dossier as a bundle mode that activates the conditional parameters (seismic, cost, S-curve) and by explaining the default vs dossier split, which the flat schema does not convey. It does not clarify the terrain object shape or the scene dependency.

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 concrete verb and resource ('obtenir la vue projet complete') and enumerates the outputs (regulation FR/USA/CH/GB, verdict, bilan BIM, porte, livrables), plus the action=dossier variant. It is clear what the tool does, but it never distinguishes itself from close siblings like cao_bim_dossier_complet, cao_bim_reglementations, or cao_bim_terrain, which is a real ambiguity in a ~130-tool family.

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 obtenir la vue projet complete selon le TERRAIN' gives a usage condition and the action=dossier switch is explained. However, there is no guidance on when to pick this over cao_bim_dossier_complet (which appears to do the same 'dossier complet') or over the narrower siblings, so the agent must infer boundary cases.

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