US Healthcare Provider (NPI) Lookup MCP

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the batch cap and the attributes being checked, but says nothing about authentication requirements, per-NPI failure behavior, rate limits, or whether the operation is read-only.

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 definition is a single dense sentence with the action, batch limit, returned fields, and target use cases front-loaded. There is essentially no wasted text.

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 batch tool with no annotations and no output schema, the description should clarify response shape and partial-failure behavior. It lists the checked attributes and batch limit, which is useful, but stops short of explaining how results are returned per NPI.

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 50%: access_token is documented in the schema, while npis has no schema description. The description usefully adds the maximum of 50 NPIs, but does not explain NPI format or token/auth behavior beyond what the schema already says.

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: verify up to 50 NPIs, with the returned attributes listed. The batch scope distinguishes it from a single-record sibling like npi_lookup, but the description never explicitly differentiates itself from npi_lookup or provider_search.

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 clear use contexts—credentialing, billing, and payer onboarding—and states the batch limit. It does not provide exclusions or explicitly route the agent to npi_lookup/provider_search for other cases.

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

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

With no annotations, the description carries the behavioral disclosure burden. It usefully notes that the service is free and returns only the top 3 matches, but it does not explain permissions, rate limits, matching behavior, 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 is a single tightly packed sentence with the most important facts front-loaded, including "FREE" and the lookup modes. It is efficient, though the terse colon-list style leaves some ambiguity about parameters.

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?

Given five parameters with zero schema descriptions, no annotations, and no output schema, the description is not complete enough for reliable invocation. It omits organization handling, first/last name distinction, and behavioral details an agent would need to choose correct inputs.

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 0%, so the description must compensate for five undocumented parameters. It mentions NPI, state, and a vague "name" field, but does not clarify first_name vs last_name vs organization, nor which combinations are valid.

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 clear verb and resource: look up a US healthcare provider by NPI or name with state. It also names useful return fields and a result cap, but it does not distinguish this tool from sibling tools such as provider_search or batch_verify.

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?

The description implies it is for provider lookups, but it gives no explicit when-to-use guidance, no when-not-to-use cases, and no comparison to sibling tools like provider_search or batch_verify.

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

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

With no annotations, the description carries the full burden. It usefully discloses the result cap ('up to 200'), which is real behavioral information an agent needs for planning. However, it says nothing about the access_token requirement, throttling, pagination, or how results are ranked/truncated when the cap is hit.

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?

A single dense sentence that front-loads the filters and then states the result cap and use cases; nothing is padded. The cryptic 'PRO.' prefix is the only wasted token.

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 six-parameter search tool with no annotations and no output schema, the description covers filters and the result ceiling but omits the authentication flow and the meaning of the organizations_only toggle. Adequate to invoke, but short of fully self-sufficient.

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 only 17% (just access_token), so the description must compensate, and it largely does: it explains that specialty is taxonomy text with concrete examples ('Dentist', 'Physical Therapist') and that city/state/ZIP combine as a location filter. The one gap is organizations_only, which appears in the schema with no explanation anywhere.

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 resource (providers) and the two selection axes (specialty taxonomy plus city/state/ZIP), which makes the operation immediately understandable. It does not differentiate against siblings such as npi_lookup or batch_verify, and the leading 'PRO.' token is opaque, but the core purpose is unambiguous.

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?

'for recruiting, sales and referral networks' hints at the use cases, which is more than nothing, but there is no when-not guidance and no routing to npi_lookup for single-provider lookups or batch_verify for bulk validation. The agent must infer that this is the discovery/sourcing tool versus the verification siblings.

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