search_references

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

Annotations provide readOnlyHint=true, covering the safety profile. The description adds a note about Solr syntax and a cryptic instruction to check valid_s and affiliation dates, which hints at filtering or validation steps but remains vague. It does not disclose return format, pagination, or any other behavioral details, but given the annotation, a 3 is reasonable for the minimal extra context.

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 description is concise (two sentences) and front-loaded with the action, but the second sentence is cryptic and unstructured. 'Vérifier valid_s et les dates des affiliations' is ambiguous and adds little clarity. It is appropriately short but not well organized for agent comprehension.

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?

The tool has 3 parameters, no output schema, and no enums, so the description is the only source of context. It fails to explain the purpose of the 'kind' parameter, how 'rows' works, or what the output contains. The hint about valid_s and dates is too vague to be actionable. This is incomplete for an agent to call 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?

Schema description coverage is 0%, so the description must compensate. It explains that the query parameter accepts Solr syntax, but it does not explain the 'kind' parameter at all, nor does it mention the 'rows' parameter. The list of facets is not explicitly linked to parameters, leaving two of three parameters under-documented. This is a significant 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 clearly states the action (Rechercher dans AuréHAL) and lists the searchable facets (author, structure, domain, journal, doctype, instance), giving a specific resource and scope. It avoids tautology and distinguishes itself from a generic 'search' by naming multiple fields, though it does not explicitly differentiate from sibling tools like search_publications or search_structures.

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 guidance on when to use this tool versus alternatives. It mentions that query accepts Solr syntax and hints at checking valid_s and dates, but provides no context for when to prefer this over search_publications or search_structures. No exclusions or alternative conditions are given.

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