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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), yet the description adds genuine behavioural context: it is INDICATIF only, not tax advice nor a declaration, defers to a professional, is stateless, and is served via REST /api/v1/fiscal/synthese with json or pdf. That is more than the annotations convey, though return shape and limits are still thin.

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 is correctly front-loaded, but the text is dense and repetitive — 'INDICATIF' and 'À titre indicatif' convey the same caveat twice, and the REST endpoint/format detail crowds an already long run-on. It stays readable but several clauses could be cut without loss.

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 no output schema, the description must indicate the return, and it does (JSON via REST or PDF). Combined with the statutory thresholds and the indicatif/not-advice framing, an agent has enough to call it correctly; only the structure of the returned comparison is left implicit.

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 already documents all seven parameters including the format enum and the bank-window address note. The description only restates the two required inputs (recettes_brutes + charges_deductibles) and the json default, adding no format or range detail beyond the schema.

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: a fiscal synthesis of revenus fonciers comparing micro-foncier (abattement 30 %, seuil 15 000 €) against régime réel (2044). An agent can tell precisely what it computes, though no sibling is named even though the surrounding toolset contains rental-related tools like regularisation_charges or crg_proprietaire.

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?

Explicit trigger: 'QUAND un bailleur se demande s'il a intérêt au micro-foncier ou au réel — typiquement à l'approche de la déclaration' gives a clear situation for calling it. No alternatives are named and no when-not-to-use boundary is drawn, which caps it below 5.

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