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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds genuine behavioral context beyond them: relevance-ordered results, the {id, title, url} document shape, and the two-step search-then-fetch pattern.

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?

The corpus enumeration is long but front-loaded and genuinely useful for scoping; the return shape and sibling routing follow in short clauses. Slightly verbose in the corpus list (e.g. naming Flytel and À propos pages), but no sentence is wasteful.

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?

For a one-parameter search tool with a full schema coverage and an output schema, the description covers corpus scope, ordering, return shape and follow-up actions. The only gap is how the query string is interpreted (keywords vs question) and result limits/pagination, which are left implicit.

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% with a single documented 'query' parameter ('Mots-clés ou question'), so the schema carries the semantics. The description does not clarify whether keyword strings versus natural-language questions behave differently, so it adds no meaning beyond the schema.

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 (recherche) plus an explicit, enumerated corpus of what is searched (plans, border pages, guides, FAQ, glossary, themes). It also distinguishes itself from two siblings by name: fetch for reading full documents and search_comontel_knowledge for direct answers with excerpts.

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?

Gives clear routing: use this search to discover documents, then call fetch to read them, and use search_comontel_knowledge (or this tool too) when a direct answer with excerpts is wanted. It does not address the other retrieval siblings (search_offers, get_faq, get_guide, get_plan), and the wording 'convient aussi' is soft rather than stating an exclusion.

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