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

Annotations already establish readOnlyHint=true and idempotentHint=true, so the description's job is lighter. It adds useful behavioral context: the result is ESTIMÉ, it depends on the rétrocession rate supplied by the caller, and it references the legal source (CGI art. 199 undecies B). This goes beyond the annotations without contradicting them.

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 compact and front-loaded with the tool's purpose, followed by output specifics and a caveat. The source citation at the end is a minor extra but provides context for the legal basis; the structure earns a 4 rather than 5 because the title is partly repeated and the long parenthetical run-on could be slightly cleaner.

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?

With no output schema, the description does enumerate the main computed values, which is essential. It also conveys estimation uncertainty and legal grounding. It does not spell out return formatting or edge cases, but for a 6-parameter estimation tool with full schema documentation and safe read-only/idempotent annotations, the coverage is reasonably 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 coverage is 100%, so the baseline is 3. The description adds only modest parameter insight, such as linking revenu_net_imposable to the cIR and noting that the rétrocession rate is caller-supplied, but it does not materially explain individual parameters beyond the schema's own descriptions.

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 opens with 'Estime la réduction d'impôt d'un investissement Girardin industriel' and then lists the exact outputs: impôt de référence, montant remboursé, and montant maximal investissable. The tool's specific object — Girardin industriel — distinguishes it clearly from the many fiscal_* and simulateurs_* siblings.

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 makes clear when the tool applies: estimating the one-shot tax reduction for a Girardin industriel investment, with the caveat that the result depends on the provided rétrocession rate. It does not explicitly name alternatives or exclusions, but the unique tax niche and the reference to the cIR de Qotien give sufficient context for an agent to route to it.

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