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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower; the description still adds real context by disclosing the return shape {id, title, url} and the two-step search-then-fetch workflow. It also hints at a coverage limit (fonction publique plus extension depending on the question), though that limitation stays vague.

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: what is searched first, then what is returned and what to do next. The parenthetical scope qualifier is slightly murky and could be sharpened, but nothing is padded.

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 one-parameter search tool with an output schema and full annotation coverage, the description covers scope, return shape, and the follow-up call. Missing are result limits/pagination and an explicit boundary against the specialized sibling search tools.

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% and the single `query` parameter is already documented as natural language or a reference (n° de requête, article). The description adds only that the searchable subject matter expands 'selon la question', which does not clarify query syntax or scope beyond the schema.

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+resource: searching decisions of the Conseil d'État and administrative courts, with a scope qualifier (fonction publique, élargissement selon la question). It distinguishes itself from `fetch` by pointing to it for full text, but does not clearly distinguish itself from the specifically-named siblings rechercher_jurisprudence and rechercher_texte.

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 a concrete next step: use `fetch` with the returned id to get the full text, which is genuinely useful routing. However, it never says when to prefer this generic search over rechercher_jurisprudence, rechercher_texte, or rechercher_conclusions, which is the main ambiguity given the sibling set.

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