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

Annotations already declare readOnlyHint and openWorldHint, so the description adds genuine extra context: the paid model, price ($0.002 USDC per successful call via x402 on Base, Solana or Arc), and that failed calls are not charged. That billing/failure behavior is important for an agent deciding whether to call. It stops short of describing response shape or how many records come back.

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?

Three sentences, front-loaded with the resource and returned fields, then the scope exclusion, then the cost. Every sentence carries decision-relevant information with no filler.

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 tool with an output schema and annotations, this covers purpose, scope limits, and pricing, which is most of what an agent needs. The only gap is that it doesn't point to a sibling for label or safety lookups when the exclusion applies.

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%, with both 'generic' (3-60 char established name) and 'limit' (1-10, default 5) documented in the schema. The description restates that the query is by generic drug name but adds no syntax, formatting, or limit guidance beyond what the schema already carries, so the baseline 3 is appropriate.

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?

Names a specific verb and resource: FDA Drugs@FDA approval records from openFDA, keyed on a generic drug name, and enumerates the fields returned (application number, sponsor, brand name, ingredients, marketing status, latest submission date). It also draws a scope boundary ('Approval records only; not a full label or safety data'), which separates it from label/safety siblings such as b2b_openfda_drug_ndc.

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 context for when the tool applies ('for a generic drug name') and an explicit exclusion ('not a full label or safety data'), so an agent knows when to look elsewhere. It does not name a concrete alternative sibling for label or NDC lookups, so the routing is implied rather than prescribed.

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