evidence_search

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

No annotations are provided, so the description carries the full burden. It discloses an important behavioral nuance: 'Presence flags are descriptive: reports a sensitivity metric is not reports a comparable sensitivity — analysis units differ across devices.' This warns the agent about interpretation of results. It also states it returns 'matching records with their parsed evidence.' However, it does not mention pagination, rate limits, or any destructive side effects (though none expected).

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 a single paragraph of three sentences, front-loading the purpose and filters. Each sentence serves a purpose: stating action, listing filters, answering user intent, clarifying result semantics. It is concise with minimal redundancy, though it could be slightly more structured (e.g., separate sentences for the caveat).

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?

Given the tool has 7 parameters, no annotations, and no output schema, the description covers the core filtering purpose and flag semantics. However, it lacks details on output format, pagination, and how to handle empty results. It does not differentiate from sibling tool 'evidence_cohort_stats' or 'device_evidence_lookup'. Completeness is adequate but not thorough.

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 71% (5 of 7 parameters have descriptions). The description adds little beyond the schema: it groups parameters but does not provide new semantic details. For example, 'has_clinical_data' lacks a schema description and the tool description doesn't elaborate. Baseline 3 is appropriate since the schema already documents most parameters adequately.

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's purpose: 'Find AI/ML device clearances by filter' and lists specific filter criteria (product code, panel, applicant, clinical data, sensitivity metric, PCCP). It answers a user question ('what evidence did FDA accept for devices like mine'), making the purpose unambiguous and distinct from sibling tools like 'device_evidence_lookup' which likely targets a single device.

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 when to use the tool: to search for evidence by filter criteria. It provides context ('answers what evidence did FDA accept for devices like mine') but does not explicitly state when to avoid it or mention alternatives among the 13 sibling tools. The guidance is clear enough for an agent to infer usage, but lacks exclusionary guidance.

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