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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the external-lookup, non-mutating nature is partly covered. The description adds that answers are verified and carry confidence and expiration, plus a no-personal-data caution for context, but does not elaborate on latency, source freshness, or failure 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?

Purpose is front-loaded in the first sentence, followed by the domain value list and the context note. The long domain enumeration is functional rather than filler, though the whole is slightly dense.

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, so return values need not be re-explained, yet the description helpfully previews them. With domain values and context documented, an agent has enough to call the tool correctly despite the 0% schema coverage.

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 0%, so the description must compensate, and it does: it enumerates the accepted domain values and explains what context is for (the current task, without personal data). Only 'question' is left to common sense, which is reasonable.

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 (pose une question) and resource (question factuelle), and even summarizes the returned artifact (réponse vérifiée avec sources, confiance, expiration, request_id). The purpose is clear, but there is no explicit differentiation from the sibling tools calculate and feedback.

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 word 'factuelle' implicitly scopes usage to factual questions needing verified answers, which is useful direction. However, there is no statement of when to prefer this over calculate or feedback, and no exclusions or prerequisites are given.

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