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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description still adds real context beyond them: results are short answers validated by the editorial team, rendered in Markdown, and include a direct link per question plus the source page.

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, front-loaded with scope, then the usage routing. Every clause carries information: corpus, answer nature, format, and links.

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 needn't be detailed, and the description still previews result shape (Markdown, link, source page). It could add what happens on zero results or coverage limits, but nothing essential for correct invocation is missing.

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% and both parameters are documented in the schema itself (keywords/question in French, max results). The description only echoes 'question précise' and adds no syntax, language or limit guidance beyond that, so baseline 3 applies.

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 and resource ('Recherche dans les questions fréquentes d'Elfy.Life') and narrows the scope to two concrete FAQ corpora, which separates it from search_content. It also names the follow-up sibling get_article, so an agent can distinguish it from alternatives without opening a 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?

'À privilégier pour une question précise' gives a clear selection context, and 'pour approfondir, lire l'article source avec get_article' names the alternative and the condition that switches to it. No explicit exclusion against search_content or the calculators, so it stops short of a full when/when-not map.

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