Search clinic documents

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

Annotations already mark the tool as read-only and non-destructive. The description adds critical behavioral context: the similarity floor gate and the explicit instruction to not fabricate answers from weak matches. This goes beyond the annotation metadata.

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 two concise paragraphs. The first sentence immediately states the purpose and method. The second paragraph details return behavior and constraints. No extraneous information.

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 an output schema (as indicated by context signals), so return values are already documented. The description sufficiently covers the search behavior, the relevance gate, and the instruction against fabrication. It is complete for the tool's complexity.

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 coverage is 100% for both parameters (query and top_k). The description adds no additional meaning beyond what the schema already provides. Baseline score of 3 is appropriate.

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 tool performs a 'hybrid-search' of the 'clinic knowledge base' with specific methods (pgvector + full-text, RRF-fused). This distinguishes it from sibling tools like get_patient_record, list_appointments, and create_appointment, which deal with patient data and scheduling.

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 explains that the tool returns cited chunks only when a similarity floor is met, and otherwise returns status=no_relevant_sources with an empty chunk list. It advises not to fabricate answers from weak matches. However, it does not explicitly state when to prefer this tool over siblings or provide when-not-to-use guidance.

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