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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds significant behavioral context: 'Mismatched, conflicting, or unverifiable citations are counted and withheld' and 'Stored claim prose is never emitted without claim-level verification.' It also notes 'Contains no affiliate links,' which is useful trust information. This clearly exceeds what annotations alone convey.

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 several sentences long but each sentence adds value: main function, filtering behavior, safety disclaimer, and usage restriction. It is front-loaded with the core purpose and then expands with necessary caveats, though slightly lengthy for what it covers.

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's moderately complex filtering behavior and the presence of an output schema, the description provides strong contextual coverage: scope, verification process, restrictions, and intended use. It lacks explicit parameter explanations, but the output schema compensates for return value details, making it largely complete.

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?

With 0% schema description coverage, the description carries full responsibility for explaining parameters. However, it only hints at 'supplement-goal record' (implying supplement and goal) but does not explain limit, year_from, year_to, or study_type. This leaves the agent without meaningful guidance for these parameters.

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 function: 'Return only PubMed-cache-verified citations that pass the repository source-accuracy audit for a published supplement-goal record.' This is a specific verb+resource+scope combination that distinguishes it from siblings like search_evidence or get_evidence_summary by focusing on claim-level citations.

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 provides explicit usage restrictions: 'Use only for public, non-personal evidence questions' and explicitly forbids use for personal health information, directing users to healthcare professionals. However, it does not name specific alternative tools or explicitly contrast with siblings, so it falls short of a 5.

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