search_reviewed_ivd

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

With no annotations provided, the description carries the full burden and delivers extensive behavioral disclosure: decision_support_only, verify_current_official_source, not_validated_for_hospital_deployment, and not_for_procurement_or_equivalence. It also warns about not inputting patient data, clarifies that each result is only a summary, states the returned content is official source text rather than AI instructions, and prohibits direct use as promotional material.

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 tool's purpose is front-loaded and every clause carries distinct value, but the text is a dense block of caveats without visual structure. It is efficient but slightly harder to parse due to the quantity of constraints packed together.

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 description covers critical constraints, result granularity, routing logic, and output nature, which is strong for a search tool. However, it omits semantics for three of the four parameters and does not clarify how offset or manufacturer interact with the search, leaving an agent with gaps in execution knowledge.

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 for all parameters, but it only addresses limit (restricting it to 1–5). Query, offset, and manufacturer are left semantically unexplained. Query is central to the tool's function, and its expected format is not described; offset and manufacturer are completely unmentioned.

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 ('Search'), resource ('TFDA permit rows'), and precise condition ('classification codes were reviewed as IVD (ivd_scope=included)'). This clearly separates it from generic search tools and identifies the exact selection criterion without ambiguity.

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 gives explicit routing instructions: when candidate_matches_available is returned, use search_ivd_candidates; for complete fields, use get_license with a single license number. It also constrains limit to 1–5, clearly stating when and how this tool should be used versus alternatives.

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