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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses non-obvious behavior: a hard cap of 'Up to 20 rows per call' and a paid x402 cost model ($0.002 USDC per successful call, failures not charged) — critical context an agent cannot get from annotations. Return-format detail is left to the output schema.

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?

Two sentences, front-loaded with what the tool returns, then filters, then limits and pricing. Dense but every clause carries information; only the pricing clause is slightly outsized for a tool description.

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?

With an output schema, full parameter coverage and annotations already present, the description supplies the remaining operationally important facts (row cap, cost, filter combinations). Minor gaps around result ordering and whether filters are ANDed are the only omissions for an open-world, 4-parameter tool.

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 each parameter is already documented in the schema. The description adds the mutually exclusive framing of npi vs generic and the 20-row ceiling, but nothing about formats beyond the schema's '10-digit NPI' note — consistent with the baseline 3.

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 states a specific verb and resource ('CMS Medicare Part D prescriber rows (by provider and drug)') and enumerates the returned fields (NPI, name, specialty, state, drug, claims, fills, cost). This clearly separates it from generic provider-registry or drug-label siblings.

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 explicitly names the two access paths: 'Filter by 10-digit NPI, or by generic drug name with an optional state,' which tells an agent how to combine parameters. It stops short of stating when to prefer this over siblings like health_npi_provider_registry or health_fda_orange_book.

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