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

With no annotations, the description carries the burden. It discloses the calculation model (progressive scale, capped quotient familial, décote) and legal sources, which is useful. It does not describe return format, handling of edge cases, or side effects, but for a tax calculator the core behavior (computation) is clear.

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 sentence with no fillers. It front-loads the tax type and year before legal sources. Slightly heavy use of parentheses and dashes, but every piece earns its place.

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 calcultor tool with no output schema, the description lacks a return-value explanation. It says what it computes but not what the response unit is (tax amount in €). The input schema covers parameters, so the main gap is the output contract. Overall adequate but not complete.

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 each parameter (parts, situation, revenu_net_imposable) is already documented. The tool description adds no extra parameter-specific meaning beyond mentioning the overall methodology, so a baseline 3 is appropriate.

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 the tool as computing French income tax for a household ('Impôt sur le revenu brut d'un foyer') with specific method features (progressive scale, capped quotient familial, décote). It differentiates from sibling tools like fiscal_tmi (marginal rate) and fiscal_prelevements_sociaux (social contributions) by specifying 'impôt sur le revenu', though it lacks an explicit 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 gives clear context: it applies to 2025 income with 2026 brackets, and mentions legal sources. However, it does not state when to prefer this tool over alternatives such as fiscal_tmi or referentiel_* tools. Usage is implied rather than explicit.

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