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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the paid-access model: $0.0045 USDC per call via x402, that an unpaid call returns payment requirements rather than data, and how to retry (X-PAYMENT, PAYMENT-SIGNATURE, or params._meta["x402/payment"]). It also flags the regulatory caveat that NDC listing does not imply FDA approval — behavioral detail an agent could not get from structured fields.

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?

Purpose and scope are front-loaded, then cost and the payment retry path, with each sentence carrying a distinct fact. It is dense but not padded; the two disclaimer sentences (no label text, no FDA-approval implication) are close in spirit but serve different purposes.

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 two-parameter read-only lookup with no output schema, the description covers purpose, cost, auth mechanics, and the key data caveat. The only gap is return shape — it lists fact categories but does not say whether results come back as a record list or paginated envelope, which matters since no output schema exists.

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%, so both parameters are already documented, and the description only echoes 'by generic name' without adding syntax, matching rules, or guidance on the limit range. Baseline 3 is appropriate when the schema carries the parameter semantics.

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 opening clause names the exact resource (openFDA NDC directory), the lookup key (generic name), and enumerates the returned facts (ingredients, dosage, routes, product identifiers, marketing category). The explicit exclusion 'Not full drug-label text' cleanly separates it from recall/clearance/label-style siblings such as us_fda_recalls or product_device_clearances.

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 sets clear context for when this tool applies (NDC facts by generic name) and rules out a nearby use case (full label text, medical advice), plus it explains the exact recovery path when an unpaid call fails. It never names a sibling tool as the alternative for the excluded use cases, so routing for label text is left to inference.

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