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

Annotations already declare the read-only, non-destructive, idempotent, open-world profile, so the safety story is covered. The description adds real context beyond that: results are catalogue records only, the full book is unavailable here, and records exist in fr/en/es/pt. It still omits result format and pagination 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?

Two tight sentences, front-loaded with the core action and immediately qualified by the scope limitation and language availability. Every clause carries information; nothing is filler.

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 no output schema and 25% parameter coverage, the description should do more work: it discloses the record-only limitation but not what a result contains, how many results come back, or how query/topic are matched. Adequate as a minimum, but incomplete for a four-parameter search tool.

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 only 25% (locale is the sole documented parameter), so description must compensate. It mentions the language set (fr, en, es, pt) which loosely maps to locale, but says nothing about query, topic, or limit semantics — leaving three of four parameters undocumented.

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?

The description gives a specific verb and resource ('Cherche dans le catalogue de livres') and adds a meaningful scope caveat (only records/cards, not the full book). It does not name or contrast with the obvious sibling get_book, so the agent must infer the search-vs-retrieve distinction on its own.

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 parenthetical 'fiches uniquement : le livre entier n'est pas accessible ici' implies that full-text access must come from another tool (likely get_book), but the description never names the alternative or states the condition for choosing it. Usage is implied rather than spelled out.

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