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

Annotations already declare readOnlyHint=true, idempotentHint=true and a closed world, so safety and repeatability are covered without the description. The description adds that the calculation spans employer/employee contribution reductions and tax exemption, which hints at the output's composition, but it says nothing about required inputs, defaults (0.22 charges, 0.25/0.5 majorations, 35 h), or what the result looks like.

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?

One dense, front-loaded sentence with zero filler — the verb and the computed outputs come immediately. It is arguably too short for a 12-parameter tool, but nothing in it is wasted.

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 12-parameter, no-output-schema calculation tool, the definition leaves the agent guessing which of the two rate inputs to supply, how heuresContratHebdo affects prorating, and how the required overtime hours interact with the optional ones. The annotations are minimal (read-only only), so the description should carry more of this load than it does.

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?

At 58 % schema coverage across 12 parameters, the description only partly compensates. It maps to tauxMajoration1/tauxMajoration2 and reductionSalariale, but the crucial choix entre tauxHoraireBrut et salaireMensuelBrut, plus heuresComp10 (temps partiel) and tauxChargesNet, are left entirely to the schema. Baseline 3 is appropriate given moderate coverage.

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 ("Calcule") and a specific resource ("rémunération des heures supplémentaires") and lists the components produced: majorations 25 %/50 %, réduction de cotisations, part exonérée d'impôt. It does not name or distinguish itself from any sibling calculator (salaire_brut_en_net, conges_payes_indemnite), but the payroll-adjacent purpose is unambiguous.

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?

There is no when-to-use, when-not-to-use, or alternative routing guidance at all. An agent cannot tell from the description whether this should be called alongside salaire_brut_en_net or standalone, nor what prerequisites (hourly rate vs monthly salary) select this tool.

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