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

Annotations already indicate readOnlyHint=true and idempotentHint=true, and the description does not contradict them. It adds useful behavioral context: the tool computes a fraction of pension, continues acquiring rights, and applies changed eligibility rules after 01/09/2025. This goes beyond what the annotations alone 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?

The description is a single dense paragraph with the key mechanism and conditions front-loaded. The legal article references and source list add verifiability but also length; the core functional information could be more compact without losing value. Still, no sentence is purely filler.

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 tool with 10 parameters and no output schema, the description covers eligibility, the fraction formula, and statut-specific rules, which is substantial. However, it never explains what the tool returns, how optional parameters like rfr and parts affect the calculation, or how the result should be interpreted. There is enough information for basic use but a noticeable gap remains for a complex legal calculator.

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 80%, so the baseline is 3. The description adds real value by explaining the formula, linking statut to quotité ranges (salarié 40–80%, fonction publique 50–90%, TNS 20–60% via diminution_revenus), and reinforcing the 150-trimestres requirement. However, it does not clarify the role of rfr or parts, which remain opaque.

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 clearly identifies a progressive-retirement calculator—'Retraite progressive (fraction de pension + temps partiel)'—and states the core computation: Fraction = 100% − quotité travaillée. It also distinguishes itself from sibling retirement tools by focusing specifically on the fractional pension with part-time work, though it lacks an explicit imperative verb like 'calcule'.

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 provides meaningful eligibility context: accessible from age 60 since 01/09/2025, requiring 150 trimestres, with statut-specific quotité ranges. However, it does not explicitly tell the agent when to choose this tool over alternatives such as retraite_estimation or retraite_optimisation, leaving the comparison implicit.

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