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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is low. The description still adds real value beyond them: results come back as short summaries, results are paginated, and entries of kind "discovery" remain unverified — a data-quality caveat an agent cannot get from the annotations or schema.

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 compact sentences, with the core action and filter axes front-loaded before the output/caveat note. The second sentence is terse to the point of being slightly telegraphic ("Résumés courts et pagination"), but there is no 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?

For a 6-parameter, no-required-args search tool with no output schema and no parameter descriptions, the definition covers the essentials (filters, pagination, summary shape, discovery caveat). It still omits defaults for limit/offset, ordering behavior, and what a result record actually contains, which matters more here because no output schema exists.

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 0%, so the description must carry the load. It maps the filter axes to parameters (thème/q, type/kind, statut/status, couverture/coverage) and alludes to pagination (limit/offset), but it does not explain the free-text q versus the string status/coverage fields, nor the enum meaning of kind beyond the discovery caveat.

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 ("Rechercher") and a specific resource ("les sources publiques de La Réunion") and enumerates the filter axes (thème, type, statut, couverture). It is clearly a search/list operation, but it never distinguishes itself from close siblings such as query_reunion_source, read_research_source, or browse_public_information.

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 filter axes named, which signal "use this to find sources matching criteria," and the caveat about "discovery" hints at a selection nuance. However, no alternative tool is named and no when-not condition is stated, so the agent must infer routing against the many sibling search/read tools.

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