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

Annotations only cover readOnly and openWorld; the description adds operationally important behavior an agent must plan around — a per-call price of $0.002 USDC via x402 on Base/Solana/Arc, with failed calls not charged. That is real value beyond the annotations. It stops short of covering zero-result behavior or rate limits, so it is strong but not exhaustive.

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 opening sentence and the NPI-1 restriction are well front-loaded, but the middle section spends substantial length describing two unrelated tools (luxury cars, FAA aircraft tail numbers) that contribute almost nothing to invoking this tool. The pricing sentence is dense but justified; trimming the unrelated cross-references would sharpen the definition considerably.

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 present, return-shape explanation is not required, yet the description still names the fields, and it discloses the paid-call model and the individual-provider scope. For a three-parameter read tool this covers what an agent needs to call it correctly; only failure/empty-result handling is left implicit.

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% and each of the three parameters (lastName, state, limit) already carries its own format constraints and default. The description restates the search keys (last name, 2-letter state) but adds no syntax, normalization, or edge-case meaning beyond the schema, so the baseline of 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?

States a specific verb and resource — searching CMS NPPES NPI records by last name and 2-letter state — and enumerates the returned fields (NPI number, name, credential, taxonomy, practice city/state, last update). The 'Individual providers (NPI-1) only' clause sharply bounds the resource, so an agent can distinguish this from organization-lookup or other provider directories 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?

It gives the required search keys and an exclusion ('NPI-1 only'), which implies when to use it. However, the only explicitly named alternatives are gov_dupont_registry (luxury cars) and gov_faa_aircraft_registry (aircraft), which nobody would confuse with NPI lookup; meanwhile the real competing siblings (b2b_webmd_healthcare_provider_directory, b2b_doximity, b2b_ada_find_a_dentist, b2b_healthline_medical_providers_directory) are never mentioned, so routing guidance for genuinely ambiguous cases is absent.

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