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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavior: a hard cap of 10 results, result ordering rules (search-term relevance, then formations with a published figure, then alphabetical), and the neutrality note. It omits what happens with zero matches, but the substantive behavioral context is present.

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 core capability and ordering rules are useful, but two of the five sentences are rhetorical marketing questions that don't help an agent invoke the tool correctly. The ordering rule is dense and placed after the purpose, which is acceptable but not front-loaded cleanly.

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 an output schema present, the description needn't explain return structure, and it still covers result count, ordering, and neutrality. Parameter semantics are covered by the schema. Only edge cases (no results, behavior when multiple parameters conflict) are left unstated, which is a minor gap.

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%, so all three parameters (type, texte, ville) are already documented with examples. The description's phrase 'par nom, spécialité, école, ville ou type de diplôme' loosely maps to those parameters but adds no syntax, format, or combination guidance beyond the schema, so 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 names a specific verb (Trouvez/Rechercher) and resource (formations en France dans Diplomètre) plus the searchable facets: nom, spécialité, école, ville, type de diplôme. It is clearly a search tool, implicitly distinct from comparer_formations and lire_formation, but no sibling is named explicitly, and the opening rhetorical questions add noise rather than precision.

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?

Usage is implied by the framing ('Quelles études après le bac ? … Trouvez des formations'), so an agent can infer this is the entry point for discovery. However, there is no explicit when-to-use vs. when-not, and no pointer to siblings like lire_formation for detail or comparer_formations for comparison.

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