nppes-npi-registry

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

readOnlyHint=true already covers the safety profile, but the description adds real context beyond annotations: the lookup is exact-match and single-record, and it enumerates the returned sections (basic info, addresses, taxonomies, identifiers, other names). It does not mention error behavior for a non-existent NPI.

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?

Three short sentences, purpose front-loaded, then return contents, then source API. No filler and nothing repeated from the title.

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 one-parameter read-only lookup with no output schema, the description adequately sets expectations about what comes back. Only minor gaps remain (behavior on a missing or invalid NPI), which are not blocking for correct invocation.

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 the single parameter already documents the 10-digit format and an example. The description only echoes 'exact 10-digit', adding no syntax or edge-case meaning 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?

States a specific verb ('look up'), resource ('healthcare provider'), and the exact discriminator ('exact 10-digit NPI'), plus what the record contains. The contrast with the sibling search tools is implicit via 'single' and 'exact' rather than explicit, so it stops short of naming an alternative.

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?

Usage is implied: this is the tool for when you already hold a known NPI, versus the nppes_search* siblings for finding one. It never states that condition or names the alternatives, so the agent must infer the routing rule.

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?

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds a non-obvious behavioral constraint not present in the schema ('requires at least one meaningful search parameter'), which is genuinely useful since required=0 would otherwise suggest an unrestricted call is valid. It does not describe return shape or pagination behavior, so not a 5.

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?

Three tight sentences with the capability statement front-loaded, then routing, then the hard constraint. Very efficient, though the trailing 'NPPES Read API v2.1' is version trivia that contributes little to invocation.

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 read-only, 14-parameter search with full schema coverage, the description covers capability, routing, and the minimum-parameter constraint. The one gap is that no output schema exists and the description never says what a result looks like (provider record shape, count behavior), which an agent composing downstream steps would benefit from.

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% with enums and patterns on the tricky fields, so the schema carries parameter meaning almost entirely. The description only summarizes criteria categories (name, NPI, taxonomy, location) at a level the schema already conveys, adding no syntax or format detail. 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?

Specific verb ('search') + resource (NPPES NPI Registry) + explicit scope ('ANY combination of criteria' with the criteria domains enumerated). It directly names the two sibling tools it is not and the condition that selects it, so an agent can distinguish it without opening a 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?

Explicit routing: 'Use nppes_search_individuals / nppes_search_organizations for the common cases; use this when you need mixed or advanced criteria.' This is a textbook when-to-use/when-not statement naming the alternatives.

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?

readOnlyHint=true already establishes the safe-read profile. The description adds useful behavioral detail not in the annotations (trailing '*' wildcard matching and the 2-char minimum before the wildcard, plus the API/version 'NPPES Read API v2.1'), but it omits rate limits, result caps, or pagination behavior beyond what the schema covers.

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?

Four short, front-loaded sentences with no filler; the core scope (individual providers) leads and the important eligibility constraint follows. Slightly dense but every clause carries information.

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 an 11-parameter, fully optional, no-output-schema search tool, the description supplies the essential routing and constraint guidance. Return format is not described, but the absence of an output schema makes that a minor omission rather than a blocking gap.

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 the baseline is 3, but the description adds real value: the 2-char minimum before a wildcard for name fields is not stated in the per-parameter schema descriptions, and the taxonomy keyword examples reinforce the specialty filter. It does not expand on the enum-only parameters (name_purpose, address_purpose) which the schema already handles.

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+resource ('Search for INDIVIDUAL healthcare providers'), enumerates the criteria (name, specialty/taxonomy, location), and disambiguates from the sibling nppes_search_organizations via the emphasized INDIVIDUAL/NPI-1 framing. An agent can route between the two search tools without opening a 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?

Explicitly instructs 'Provide at least one meaningful criterion beyond a location', a genuine usage constraint, and the location/name/taxonomy framing clarifies intended search contexts. It stops short of naming nppes_search as the generic alternative or stating when-not-to-use, so it is strong but not fully complete.

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?

readOnlyHint=true already tells the agent this is a safe read, so the description is not carrying the safety burden. It adds a useful behavioral detail (trailing '*' wildcard on organization_name, min 2 chars before it) and the API version, but says nothing about result caps, pagination behavior, or rate limits for a 9-parameter search.

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 tight sentences with zero padding: the capability and its entity-type scope lead, followed by wildcard syntax and provenance. Every clause earns its place and nothing is buried.

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 9 parameters, no output schema, and only a readOnlyHint annotation, the description covers the primary search dimensions (name, specialty, location) but omits what the call actually returns (NPI record shape / fields) and gives no pagination or result-limit context. Adequate but with clear gaps for a search tool of this breadth.

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 all nine parameters are already documented by the schema; baseline is 3. The description's wildcard note is essentially a restatement of the organization_name schema text and it does not clarify the relationship between address_purpose and the location filters.

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 (Search) and resource (ORGANIZATION healthcare providers, NPI-2), and enumerates concrete examples (hospitals, clinics, group practices, pharmacies, labs). The uppercase 'ORGANIZATION' plus the NPI-2 designation cleanly distinguishes it from nppes_search_individuals and nppes_lookup_npi without opening any 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?

The scope statement implies when to reach for this tool (entity-type 2 organizations rather than individuals), but no sibling tool is named as an alternative and there is no explicit when-not guidance. Usage is inferable rather than stated.

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