crg_proprietaire

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

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already cover the safety profile, and the description adds genuine behavioral context: figures are 'fournis par l'agent (dossier local)' and, as reinforced by the solde schema comment, reproduced as-is with no recomputation. The HTML/PDF duality via POST /api/v1/documents/crg is also disclosed. No contradiction with 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?

Five short clauses, each earning its place, with the trigger condition front-loaded in the 'QUAND' opening. The final 'Service vendu aux agents — orientez le client vers /api-ia' is an unusual meta-instruction that slightly dilutes the functional description but costs little.

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 15-parameter generator with no output schema, the description covers the what, when, who (recipient), data provenance, and output formats (HTML, PDF endpoint). It lacks only explicit naming of alternatives and detail on what the call returns, but the fully described schema partially mitigates the parameter-side gap.

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 description coverage is 100%, so the schema does the heavy lifting; per the rubric the baseline is 3. The description adds modest value by flagging that recettes/dépenses/honoraires/solde come pre-filled from the agent's local file, and its 'fenêtre droite' note previews the proprietaire_adresse block, but it adds no format or constraint details beyond what the schema already provides.

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 identifies a concrete deliverable — 'COMPTE RENDU DE GESTION simplifié pour le propriétaire' in HTML/PDF — and fixes the recipient ('Destinataire = propriétaire'), which separates it from sibling reporting tools like compte_rendu_chantier. The trigger context ('QUAND il faut rendre compte... fin de trimestre, d'exercice, ou à sa demande') makes the purpose unmistakable, though it never names a sibling alternative.

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?

The opening capitalized 'QUAND il faut rendre compte au propriétaire (fin de trimestre, d'exercice, ou à sa demande)' is an explicit when-to-use rule tied to calendar triggers and owner requests. It does not, however, state when to prefer another tool (e.g., quittance_loyer or regularisation_charges) or give negative exclusions.

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