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

Goes well beyond the annotations by disclosing cost ($0.01 per call), the payment rails (x402 USDC on Base via _meta["x402/payment"], MPP/tempo on the HTTP URL /v1/npi/verify), the batch ceiling (1-10 NPIs), and the upstream data sources. An agent knows the price, how to pay, and what it is actually reporting before calling.

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?

Front-loads the cost and payment terms, which is the most decision-relevant fact for a paid endpoint, then packs scope and disclaimers tightly. The final sentence runs long with semicolon-chained clauses, but each clause (pricing, payment, coverage, disclaimer) earns its place.

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?

Covers pricing, payment mechanics, batch limits, returned fields and the liability disclaimer; an output schema exists so return structure need not be restated. The one unresolved gap is how it relates to the exclusions_screen sibling given it also surfaces LEIE exclusions, which leaves a routing ambiguity for the agent.

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% and the schema already documents NPIs as 1-10 ten-digit values with valid check digits and no duplicates. The description's '1 to 10 NPIs' clause adds no information beyond the schema, so the baseline 3 applies.

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+resource (npi_verify) and then enumerates exactly what is returned: CMS NPPES status (active/deactivated with dates), provider/org name, practice city/state/ZIP and taxonomies, plus any HHS-OIG LEIE exclusion. An agent can distinguish this from license_verify, exclusions_screen and entity_lookup without opening the schema.

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?

States clear negative scope ('not a credential check and not a determination about the provider') and a hard input bound (1 to 10 NPIs), which tells the agent when this tool is inappropriate. However, it never names a sibling or a condition for choosing it over exclusions_screen, whose screening role overlaps with the LEIE portion here.

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