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

No annotations are provided, so the description carries the full behavioral burden. It discloses the estimation method (carrière reconstituée, SAM capped at PASS, décote), the output shape (central point, range, confidence level), and the approximate/uncertain nature of the result. It also cites concrete source rules and the 2026 PASS value, giving the agent a transparent model of what the tool does.

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 description is front-loaded with the core purpose, then the output, then a clear caveat, and finally source details in a parenthetical. It is longer than a minimal description, but every part carries decision-relevant information such as uncertainty, outputs, and methodology. The structure is organized and scannable.

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 an estimation tool with no annotations and no output schema, the description covers the essential context: inputs, output structure, uncertainty, and methodology. The main gaps are the absence of a named sibling for the precise-calculation case and the apparent schema inconsistency around the required statut and age fields. Overall, an agent can reliably select and invoke this tool from the description.

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?

Although schema coverage is high, the description adds useful meaning by naming the core inputs: statut, revenu, âge, âge de départ, and by specifying that traitement indiciaire applies to fonctionnaires. This is particularly valuable because the schema snippet omits a statut property and appears to conflate age with age_depart. The description does not redundantly restate every schema field.

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 opens by stating 'Estimation de pension (données partielles)' and 'Pension approchée', which immediately identifies the tool as an approximate pension estimator. It explicitly says 'Ce N'est PAS un calcul certain' and explains that it replaces a missing RIS career statement, which distinguishes it clearly from exact pension calculation siblings.

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 description gives a clear when condition: use it when a RIS career statement is missing, and a clear when-not: it is not a certain calculation and is not a substitute for a precise pension calculation when the RIS is available. It does not name a specific sibling tool to use in the precise-calculation case, so it stops short of full alternative routing.

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