Rechercher dans Judilibre

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

With no annotations, the description carries the full burden, but it does disclose two genuinely useful traits: the corpus is open and pseudonymized, and results are not a criminal record and must be qualified by the company's role. It says nothing about pagination, result volume, rate limits, or any authentication/permission requirement, so the behavioral picture is only partial.

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 short sentences, front-loaded with the core purpose and no padding. The second sentence is a legal qualification caveat rather than operational detail, but it is short and arguably relevant to correct interpretation of results.

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 10-parameter search tool with no annotations and no output schema, the description is far too thin: it explains neither the filter parameters nor anything about the shape or pagination of results. The legal caveat is valuable but does not cover the operational information an agent needs to call this correctly.

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?

There are 10 parameters at 0% schema description coverage, yet the description names none of them — types, fields, jurisdictions, date_start/date_end, page, page_size, sort and order are all undocumented anywhere. Only the existence of a free-text query is weakly implied by 'Recherche', so the description fails to compensate for the coverage gap.

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 ('Recherche') and a specific resource ('décisions judiciaires ouvertes et pseudonymisées'), so an agent immediately knows this is a full-text search over open case law. It does not, however, distinguish itself from the sibling get_judilibre_decision (search vs. fetch a single decision), leaving that routing to inference.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as get_judilibre_decision or search_adlc_sanctions. The second sentence is a legal caveat about qualifying results, not usage guidance, so the agent gets no selection criteria.

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