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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds meaningful context: it is stateless, based on the law text with a BOFiP expected, and explains the formula (80% of price, rate based on type, cap, deductible). It also warns that calculations are provisional pending BOFiP. This goes beyond the annotations and gives the agent a clear model of the tool's behavior.

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 long but dense and well-structured, with a warning about BOFiP and sources at the end. Every sentence contributes either to purpose, formula, or caveats. It is front-loaded with the core purpose and device name. It is not overly verbose for the complexity of a French tax incentive calculation.

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 no output schema, the description clearly states what it returns (annual depreciation and tax savings for 1 and 9 years). It explains all input parameters' roles (though the schema does too) and adds the legal basis and caveat about BOFiP. For a read-only calculator with idempotent behavior, nothing essential is missing for an agent to call it 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 coverage is 100% with each parameter described. The description adds value by explaining the 80% amortizable basis (terrain forfait 20%) and the TMI override logic (tmi_pourcentage bypasses derivation from revenu_net_imposable). This is beyond what the schema states, enriching the meaning of the parameters.

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 a specific verb ('Calcule') and resource ('amortissement annuel retenu et l'économie d'impôt'), identifies the device (Dispositif Jeanbrun, successeur de Pinel), and provides the legal reference (LF 2026 art. 47). It is unmistakably distinct from the many other fiscal_* siblings because it names a unique tax incentive with a specific calculation scope.

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 explains the tool's role and context (successor of Pinel, window 21/02/2026→31/12/2028) but does not explicitly name alternative tools or state when not to use it. However, the specificity of the device makes it obvious which scenario it addresses. It lacks an explicit 'use X instead' pointer, which the high example had, so not a 5.

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