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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, and 'Lecture seule' merely restates that. The description earns credit for adding the reliability caveat (results are indicative, real FDES required for regulatory study) and clarifying what each action mode produces, which goes beyond the annotations.

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?

Front-loaded with the trigger and dense with useful detail; separators (| and : ) make it scannable. It runs long as a single stream, but nearly every clause carries information an agent needs.

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 5 params, a nested scene object and no output schema, the description carries the return burden and does so by naming the outputs (total, ratio kgCO2e/m2 vs RE2020 thresholds). Return shape for verifier/suggestions modes is only partly implied.

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 baseline is 3, but the description adds genuine meaning: it explains what action=verifier (verdict indicatif) and action=suggestions (substitutions et carbone evite) do, which the schema lists only as bare values, and it enumerates what the scene object contains.

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?

States a specific verb (estimer) and resource (le carbone/ACV d'une scene), and details the computation method (quantites x facteurs FDES/INIES, total + ratio kgCO2e/m2). It does not explicitly distinguish itself from closely-named siblings like cao_re2020 or cao_energie, so an agent must infer the embodied-vs-operational distinction itself.

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?

'Appelez quand vous devez estimer le CARBONE de la construction' gives a clear triggering condition, and the 'Indicatif — l'etude reglementaire exige les FDES reelles' caveat signals a boundary. No alternative sibling is named, so the agent has context but no explicit routing.

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