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

Annotations already declare readOnlyHint/non-destructive/closed-world, and the description adds genuinely new context: the result is "Indicatif — marché et CCTP signés priment", i.e. advisory output that must defer to signed contract documents. It also signals the output is a structured read of four sub-blocks. No pagination or error behaviour, but the advisory caveat is the important non-obvious trait.

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 the trigger and the resource, followed by the section list and two short caveats; every clause carries information. The telegraphic abbreviation style (PQ-PLAN, PQ-NC, PAQ) is dense but consistent with the surrounding tool family.

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 one-parameter read-only tool with no output schema, the description supplies the returned structure, the read-only nature and the authoritative-source caveat, which is enough for correct invocation. Missing only explicit sibling routing, which is the notable remaining gap given the namespace size.

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% and the single parameter is documented, so the schema already carries the load; the description repeats the same {plan, controles, enregistrements, nc} shape. It does add a small amount by expanding each key (contrôles/points d'arrêt, enregistrements/fiches, non-conformités/actions), which helps interpret the nested object, but gives no format or validation detail. 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?

Names a specific verb (VERIFIER) and resource (PLAN QUALITE / PAQ) and enumerates the four sections it reports on (PQ-PLAN, PQ-CONTROLES, PQ-ENREGISTREMENTS, PQ-NC), which pins down scope precisely. It does not differentiate from overlapping siblings such as cao_bim_points_arret, cao_bim_qai or cao_bim_conformite, so it falls short of a 5.

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 PLAN QUALITE" gives a call trigger, but it essentially restates the purpose rather than routing the agent. No when-not conditions and no named alternatives despite a very crowded cao_bim_* namespace with plausible overlap (points d'arrêt, QAI, conformité).

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