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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), and the description adds genuine behavioral detail beyond them: pensionNetMonthly is null unless rfr is provided, and without rfrPrecedent the median/normal rate is skipped and the result is a reduced-rate estimate. This conditional-output behavior is exactly the kind of context annotations cannot convey.

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-loads the purpose, then groups inputs, then output behavior in three sentences with no filler. Dense but every sentence carries information; only the long input enumeration is slightly list-like.

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 13-parameter tool with nested objects, no output schema, and thin schema descriptions, the definition covers purpose, the key output field (pensionNetMonthly) and the rfr/rfrPrecedent conditions well. Remaining gaps concern the meaning of the less-common numeric inputs, which lowers it from a 5.

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 only 23%, so the description must compensate: it enumerates most inputs (birth year/month, retirement age, regime, SAM, quarters, Agirc-Arrco points, liberal-career elements, rfr/rfrPrecedent) and clarifies the rfr/rfrPrecedent relationship (previous year = rfr year minus one). But it gives no semantics for samSaisi, trimestresRG, pointsCNAVPL, etc., so the low-coverage gap is only partly filled.

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 ("Estime") and resource ("pension de retraite brute"), so an agent knows exactly what is computed. It is clearly distinct from the simulate_* siblings by domain (retirement pension), though it never names or routes to an alternative explicitly.

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?

Implicit guidance is present: the description explains that the result is "indicatif" without rfrPrecedent and that the net field is only populated when rfr is supplied. However, there is no explicit when-to-use / when-not-to-use framing or reference to the many simulate_* sibling tools.

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