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

With no annotations provided, the description carries disclosure itself. It states the calculation basis (Circulaire CNAV 2026-04 barème), the two options, the income-tax deductibility effect, and the legal limits. It does not spell out the exact output shape or behavior when optional inputs are omitted, but the core behavioral guarantees are well covered.

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 core function and outputs are front-loaded, with legal source strings at the end for verifiability. There is slight redundancy between 'Rachat de trimestres (VPLR — coût, gain, ROI)' and 'Coût et rentabilite d'un rachat de trimestres', and the paragraph is dense, so it stops just short of a 5.

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 no output schema, the description covers the essentials: inputs (âge/option/revenu), outputs (coût net d'IR, gain de pension, ROI), and special cases (études, stage, legal cap). The exact return object and behavior with omitted options are not documented, but the schema covers parameter constraints and the description names the key computed values, which is sufficient for a competent agent.

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 69%, so the description adds needed context: it connects age, option, and revenu to the barème, names the two option values, and gives legal constraints for motifs and number of quarters. It does not individually elaborate all 13 parameters, but the determinant inputs and their role in the calculation are made clear.

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 leads with the precise domain — 'Rachat de trimestres (VPLR — coût, gain, ROI)' — and states what the tool computes: the cost, tax-net cost, pension gain, and ROI of buying retirement quarters. The legal basis and barème details make it unmistakably distinct from sibling retirement tools such as retraite_estimation or retraite_optimisation.

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 clear context for when the tool applies: any rachat de trimestres calculation, with explicit coverage of études (abattement ≤ 40 ans), stage (12 % PMSS), and the 12-trimestre legal cap. It does not explicitly name sibling tools to exclude, but the scenario is specific enough that an agent can route to it without ambiguity.

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