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

No annotations are supplied, so the description bears the full burden. It does disclose the return shape (titre, URL, extrait) and that results are relevance-ranked ("les plus pertinentes"), but says nothing about search mechanics — keyword vs semantic, language of the corpus, whether full text or abstracts are matched, or cost/latency limits.

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?

Three compact sentences with zero filler, front-loading the corpus identity before return values and the citation rationale. The parenthetical topic list is slightly long but earns its place by scoping what the corpus covers.

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 two-parameter read-only search with fully documented schema and no output schema, the description covers corpus scope, return fields, and intended use. It leaves only secondary details (ranking method, corpus size/language, result-count behavior) unstated.

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%: both q and k (with its 1–12 range and default 5) are documented in the schema itself. The description adds only the implied relevance framing ("les notes les plus pertinentes"), which does not extend parameter meaning beyond the schema, 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 ("Cherche") and resource ("corpus de notes de Pierre-Jean Tribot"), and enumerates the thematic scope (IA, culture, patrimoine, géopolitique, etc.) plus what a result contains (titre, URL, extrait). It does not name the sibling it is not — notably search_baltic_finnish_architecture, another corpus search — so an agent must infer from the corpus name which search tool applies.

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 explicit usage guidance: "À utiliser pour citer sa pensée à la source plutôt que de la paraphraser de mémoire", which tells the agent the trigger condition (quoting sourced thinking instead of recalling from memory). No exclusions or named alternatives are provided, so it stops short of full when/when-not routing.

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