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

The annotations already declare readOnlyHint=true and idempotentHint=true, covering safety and side effects. The description adds meaningful behavioral detail beyond the annotations: the 10,000 € / 18,000 € thresholds, the list of excluded niches (dons Coluche, Malraux, Monuments historiques, déficit foncier, PER), and the legal sources. This substantially helps an agent understand what the computation respects.

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 tightly written: the main purpose and thresholds are front-loaded, followed by exclusions and input note. The sentence 'La liste des niches est fournie en entrée' is somewhat redundant with the schema, and the legal citations are extra, but they are relevant and do not bloat the description.

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 tool has no output schema, the description should state what the tool returns (e.g., the calculated capped tax reduction or the total reduction after global capping). It does not. It covers the rule, thresholds, exclusions, and input well, but the missing return contract is a real gap for an agent selecting and invoking the tool.

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 the schema already documents the single `niches` array parameter and its object shape. The description adds domain context about which niches are in or out of the cap, but it does not expand on the accepted `type` values beyond the schema examples, nor does it clarify output semantics.

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 title and description clearly identify the resource: the global cap on tax niches ('Plafonnement global des niches fiscales') under CGI art. 200-0 A, with the main thresholds stated. It is distinguishable from sibling tax tools (e.g., fiscal_impot_revenu, fiscal_ifi) by its specific focus on niche capping. However, it lacks an explicit verb such as 'calculate' or 'returns', and does not explicitly name sibling distinctions.

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 implies when to use the tool: when applying the global cap to a provided list of tax advantages. It also clarifies important scope exclusions ('Certaines niches sont HORS plafond'). It does not explicitly describe when not to use it or point to alternative tools, leaving routing partially implicit.

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