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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely new context by stating what the tool does NOT return ("Ne renvoie ni questions ni résultats"), which prevents an agent from expecting test items or scores. It stops short of describing pagination or ordering behaviour.

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 short, front-loaded sentences: what is searched, how it filters, what it does not return. No filler and no repetition of the title.

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 4-parameter, no-output-schema search tool, the definition covers scope, filter mechanism and the key negative about return content, which is the main ambiguity an agent would face. It could still say more about result shape or how limit interacts with the 206-item corpus, 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 75%: query, category and locale carry their own descriptions (locale quite thoroughly). The description only echoes keywords and theme, adding the combinability nuance but saying nothing about limit or how category slugs relate to free-text query. With the schema doing most of the work, the 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?

The description gives a specific verb ("Cherche") plus the resource and its scope ("206 tests psychologiques (fiches)"), which cleanly separates it from the singular get_test and from search_articles/search_books. It does not explicitly name a sibling to contrast with, so it stops short of a 5.

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?

"Filtre par mots-clés et/ou thème" implies how the tool is used, and the phrase "et/ou" signals the filters are combinable. But there is no explicit statement of when to pick this over get_test (browse/search vs. fetch one known sheet), so usage is only implied.

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