lu_dp_search_decisions

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

No annotations are provided, so the description carries the burden of behavioral disclosure. The description usefully states it returns 'matching decisions with reference, entity name, fine amount, and GDPR articles cited,' which is helpful forward-looking context. However, it doesn't disclose pagination/limit behavior, case-sensitivity, relevance ranking, or what a zero-result response looks like.

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?

A single well-formed sentence that front-loads the core purpose and adds return value detail efficiently. No wasted words, though it could marginally tighten the parenthetical list of decision types which are partially restated in the type param enum.

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 search tool with 100% schema coverage and no output schema, the description conveys the core behavior (what is searched, what is returned). It's reasonably complete for a filtered-full-text-search tool, though it lacks explicit guidance on using topic/type filters together or result count handling, which the limit param implies.

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 the schema already documents all 4 parameters and their meaning. The description adds the return-field context (reference, entity name, fine amount, GDPR articles) but doesn't add extra meaning about the parameters themselves beyond the schema, hence the baseline 3.

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 has a specific verb+resource ('Full-text search across CNPD decisions') and clearly distinguishes from siblings: it searches decisions (vs lu_dp_get_guideline which retrieves guidelines, lu_dp_search_guidelines which searches guidelines, and lu_dp_get_decision which retrieves a single decision). It enumerates decision sub-types and return fields, giving clear scope.

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?

The description implies usage context (searching the CNPD decisions corpus) and the French-language requirement is explicit in the query param ('Search query in French'). However, it doesn't explicitly state when NOT to use this vs lu_dp_get_decision, which would be its closest sibling, though the verb split (search vs get) implies the distinction.

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