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

Annotations already cover read-only, non-destructive and closed-world, and the description reinforces this with "Lecture seule". The genuinely added context is the reliability caveat that this is indicative data and the signed contract/CCTP prevails, which changes how the agent should present the result. It stops short of saying what the response contains.

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 dense paragraph with the trigger condition front-loaded and the caveat placed last where it reads as a qualifier. The enumeration is necessary for scope; nothing is redundant, though the repetition of the key list in both sentence and schema-mirroring form is slightly wasteful.

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 read-only single-parameter tool the invocation side is adequately covered, but with no output schema the description never indicates what the returned dossier looks like (field set, empty-state, per-axis presence). The caveat helps, but return-shape guidance is missing.

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 at 100% schema description coverage, the schema already labels the nested scene object and its four keys; the description mirrors that content rather than adding to it. It does supply the EX-* codes, but not the expected shape or completeness of each sub-object.

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 in caps ("VERIFIER LE DOSSIER D'EXPLOITATION") and enumerates the four content axes (dossier, consignes, interlocuteurs, suivi) with their codes. It does not differentiate from nearby siblings such as cao_bim_dossier_complet, cao_bim_cctp or cao_bim_intervenants, which is the main gap.

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 LE DOSSIER D'EXPLOITATION" gives an explicit invocation condition, and "Indicatif — marche et CCTP signes priment" tells the agent what to fall back on when the data is insufficient. No sibling alternative or exclusion is named, so the agent cannot tell when to pick cao_bim_cctp or cao_bim_dossier_complet instead.

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