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

Annotations already cover read-only, idempotent, open-world and non-destructive semantics, so the bar is lower. The description adds real value beyond them: results are ordered newest first, a source is named (openFDA PMA database), and it warns that most results for large makers are manufacturing/labelling supplements rather than new devices — a behavioral caveat that prevents misinterpretation. It omits only pagination/result-cap behavior, which the schema's limit parameter covers.

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?

Front-loaded with purpose, then fields returned, audience, source, sibling relationship, and the supplement caveat — every clause carries information. The audience sentence ('For regulatory affairs teams and investors…') and the trailing '(cost: 1 credit)' are the least load-bearing parts but still orient the agent.

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?

There is no output schema, so the description carries the return-value burden itself — and it does, enumerating PMA/supplement numbers, decision, supplement type and reason, and FDA's approval statement. Combined with the ordering note and source attribution, an agent has everything needed to call and interpret the result.

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 100%, so all three parameters are documented in structured fields; baseline 3 applies. The description's 'by applicant and/or trade name' does clarify that the two filters can be combined rather than being mutually exclusive, which is a small addition beyond the schema.

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?

States a specific verb and resource: 'Finds US FDA premarket approval (PMA) decisions for high-risk Class III devices, including supplements,' and names the distinguishing sibling 'fda_device_510k_clearances'. An agent can immediately tell this apart from the 510(k) clearance tool.

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?

Gives clear selection context (high-risk Class III devices, implants, heart valves, pacemaker leads) and explicitly frames itself as complementary to fda_device_510k_clearances. It does not state an explicit when-not rule (e.g., use 510k for moderate-risk Class II), but the risk-class framing makes the split inferable.

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