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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the bar is lower. The description still adds material context beyond annotations: a per-call price ($0.01 USDC via x402 on Solana), an alternate HTTPS endpoint, and the 'GMDN removed' data caveat. It does not describe pagination or result shape.

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?

Dense, front-loaded, and waste-free: resource, datasets, query surfaces, caveat, and pricing in a short block. The payment/endpoint note is separated cleanly rather than buried mid-sentence.

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?

For a 13-parameter read-only search tool with full schema coverage and rich annotations, the description covers scope, datasets, query surfaces, and payment mechanics. The main remaining gap is any hint about result shape or pagination interaction between skip/limit, which no output schema documents.

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 coverage is 100% with per-param descriptions and enums for dataset and deviceClass, so the baseline is 3. The description reinforces count semantics ('count by any field') and the searchable field set, but adds little that the schema does not already state.

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 resource (FDA device records) and enumerates the concrete datasets covered: 510(k) clearances, PMA approvals, classification, and GUDID/UDI. The scope implicitly separates it from siblings like fda_recalls and fda_adverse_events, but no sibling is named explicitly.

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?

It gives the query surfaces (name, product code, applicant, number, raw search, count) and notes the default dataset is 510k, which is useful context. However, it never states when to prefer this over fda_recalls or fda_adverse_events, nor any prerequisites or exclusions.

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