fda_covid_serology

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds context about the data nature (FDA evaluation, sensitivity/specificity) and hints at count fields, but does not disclose the exact return format, pagination, or whether results are records or aggregates. It does not contradict annotations, but it does not fully elaborate on behavioral traits beyond what is already given.

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 and well-structured: it starts with the purpose, provides two illustrative search examples, and lists count fields. There is no redundant or vague wording. The examples are front-loaded and directly useful, making the description efficient and scannable.

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 there is no output schema and only two parameters, the description provides sufficient context for a search tool. It explains the subject matter (serology evaluation), gives example queries, and mentions count fields. It does not explicitly describe the structure of the response (e.g., whether it returns a list of records, total counts, etc.), but the examples and focus on sensitivity/specificity imply the data contains those metrics. The tool is not overly complex, and the description covers the essential usage context.

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?

Both parameters (limit and search) have descriptions in the schema, so schema coverage is 100%. The description adds valuable examples for the search parameter, specifying valid fields like antibody_truth and manufacturer, and lists count fields (type, manufacturer.exact) that are not in the schema. This goes beyond the schema's generic query syntax and helps an agent construct meaningful queries. Limit is adequately described in the schema; the description does not add extra, but the search examples significantly enhance parameter understanding.

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 states a clear purpose: searching FDA's evaluation results for COVID-19 serology (antibody) tests. It specifies the resource (FDA evaluation data) and the subject (sensitivity/specificity), which distinguishes it from other FDA search tools like fda_drug_events or fda_device_events. The verb 'Search' is explicit, and the examples reinforce the tool's focus on antibody test performance.

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 example searches but does not explicitly state when to use this tool versus alternatives, nor does it mention when not to use it. It implies usage via examples (e.g., searching by manufacturer or antibody_truth) but lacks explicit guidance on selecting this tool over other FDA or COVID-19 related tools. The context is clear, but exclusions and alternative routing are absent.

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