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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so safety is covered. The description adds genuinely new context the agent cannot get elsewhere: a per-call price of $0.01 USDC via x402 on Solana and a mirror HTTPS endpoint, plus the default of compact (non-full) records. It still leaves some behavior unstated, such as paging limits of the raw search or error handling.

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 front-loads the datasets and filtering capabilities, then closes with the pricing and alternate endpoint in one line. It is dense but virtually every clause carries information; the only slight drag is the URL string, which is necessary operational detail.

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, fully documented, read-only query tool with no output schema, the description covers enough: which datasets, what can be filtered, compact versus full records, counts versus listings, and the cost model. An agent could invoke it correctly, though the absence of an output schema means the response shape (and paging behavior past the 25,000 skip cap) is only loosely implied.

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 the baseline is 3, but the description adds meaning on top of the schema by tying parameters together: it explains that 'count' produces aggregations on any field, with the concrete example of top reactions for a drug, and that 'search' can be used as a raw openFDA fallback. It also frames 'full' versus compact reports as an output-shape choice.

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 names the exact resource (openFDA adverse-event reports) and enumerates the three underlying datasets it spans: FAERS for drugs, MAUDE for devices, CAERS for food/supplements. That level of specificity makes it distinguishable from neighboring tools like fda_device, fda_recalls, and openfda_drug.

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 lists the filtering axes (drug, product, reaction, dates, raw search) and the two output modes (compact reports or counts), which implies when the tool is useful. However, it never states when to reach for this instead of fda_device, fda_recalls, or openfda_drug, and there are no exclusions or prerequisites beyond the price note.

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