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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it's a safe, side-effect-free operation. The description adds value beyond annotations by detailing the calculation formula, the components (IR, PFU, CEHR, majorations), and the stateless nature. It also provides legal sources. No contradiction with annotations, and the added context about the algorithm is useful.

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 dense but every sentence carries value: it states the purpose, gives the formula, names the distinct tool, and cites sources. It is front-loaded with the name and core function. Though lengthy, it is not verbose—it efficiently packs essential legal and technical detail without fluff.

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?

Given the complexity of a French tax calculation, the description provides the full formula and legal references, and the schema covers parameter defaults and constraints. However, since there is no output schema, the description does not explicitly state the return format (presumably the CDHR amount in euros). This is implied but could be clearer. Overall, it is quite complete for an agent to invoke correctly.

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 100%, so all seven parameters are documented in the schema. The description adds meaning by explaining how parameters like rfr_ajuste, impot_reference, and revenus_financiers_pfu fit into the overall formula, giving context beyond individual definitions. This clarifies the relationships between parameters, which is more than the baseline 3 for high 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?

The description clearly states the tool computes the CDHR (Contribution différentielle sur les hauts revenus) and provides the exact legal formula (art. 224 CGI). It explicitly differentiates from the sibling fiscal_cehr, naming the CEHR and its article, so an agent can unambiguously distinguish it. The verb is implicit ('compute') but the resource and scope are fully specified.

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 explicitly says 'DISTINCTE de la CEHR (art. 223 sexies)', which tells the agent this is not the CEHR tool. It also mentions 'Version stateless', implying it's a pure calculation without side effects. However, it does not explicitly enumerate when to use this tool versus other fiscal tools (e.g., fiscal_impot_revenu), though the specialized nature makes it fairly obvious. The alternative is named, so a 4 is appropriate.

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