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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds genuine behavioral context beyond annotations: the score represents material preparation out of 100, is distinct from the coverage rate, and explicitly excludes legal/compensation measures. This meaningfully clarifies what the returned number signifies.

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?

Two sentences with the core concept front-loaded. The key information (measures material preparation out of 100, separates from coverage rate) comes first, and the exclusions are packed efficiently into a single sentence with zero wasted words.

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?

An output schema exists and annotations cover safety, so return format and side-effect profile are handled. The description explains the score's conceptual meaning well, but the parameter semantics are not explained - especially the 'responses' nested object. For a tool with a nested object and an enum, the conceptual clarity doesn't fully compensate for the lack of parameter documentation.

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 0%, so the description must compensate for the schema's silence, but it doesn't mention any of the three parameters (topic_id, responses, as_of). Parameter names and the enum are mildly self-explanatory, but the 'responses' object structure (yes/no/unknown values) is left entirely undocumented in both schema and description, a real gap for an agent constructing the call.

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 states a specific verb (mesure), resource (dossier), and scale (sur 100), and explicitly separates the score from the coverage rate. It also lists what it does NOT measure (responsabilité, indemnisation, chance de gagner), which sharpens the purpose. However, it doesn't differentiate itself from the sibling scoreconso_score_offer_transparency, leaving ambiguity among the two scoring tools.

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 provides negative exclusions (what the score doesn't measure), which helps prevent misuse for responsibility/compensation decisions. But it gives no positive guidance on when to call this tool versus scoreconso_score_offer_transparency, and doesn't state prerequisites or context for invocation.

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