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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the data source ('snapshot public le plus récent depuis market_observation') and the explicit missing-data signal when no recent observation exists, which is a meaningful caveat for an agent interpreting results.

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?

A single dense sentence with the scope, the exclusion, the alternative tool, the data source and the missing-data behavior all front-loaded. Every clause earns its place, though the density is at the upper limit before it becomes hard to parse.

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 an output schema present (return values need not be explained), full annotation coverage and a fully documented parameter, the description supplies everything else an agent needs: scope, exclusions, source of truth and the empty-result signal.

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% and the single 'asof' parameter is fully documented in the schema (ISO 8601, default today). The description adds no syntax or semantics beyond that, so the baseline of 3 applies — the schema does the heavy lifting.

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 ('Lit') and resource (indicateurs forward EEX France) and enumerates the exact contract horizons covered (CAL Y+1, CAL Y+2, M+1). It also names the sibling it is not (renewal_advisor), so an agent can distinguish it without opening any schema.

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?

Explicitly bounds usage with 'sans décision contractuelle' and routes the agent to the alternative: 'pour une recommandation de renouvellement, appelez renewal_advisor'. Both the when-not and the alternative are stated, leaving nothing to inference.

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