Tuper NPI Registry

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

Annotations already cover safety (readOnlyHint, openWorldHint), but the description adds genuinely non-obvious behavior: results are exact only up to 1,200, above which the response is the literal string '1200+' with a pointer elsewhere, and a single call accepts at most 5 specialties. That cap is the key operational constraint an agent needs 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?

Three short sentences, no filler, and the core question plus scope constraint is front-loaded ahead of the caveats. Every sentence contributes a distinct fact (what it counts, the 1,200 cap, the 5-specialty limit).

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?

There is no output schema, and the description does not say how results are shaped when multiple specialties are supplied (a map per specialty, or a single number), nor does it address the entity default. For a read-only counting tool the cap disclosure is strong, but these two gaps keep it at minimum viable.

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 only 25%, so the description must carry the load, and it covers specialty, state and ZIP-prefix narrowing plus the 'up to 5 specialties' limit. It says nothing about the `entity` enum, whose default is 'individual' — an agent could reasonably read 'how many providers' as all entities and silently get individual-only counts.

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 — counting NPI Registry providers by specialty, optionally narrowed by state or ZIP prefix — and the 'how many' framing makes clear this returns counts, not records. It never names a sibling such as search_providers or lookup_npi, so differentiation is implicit rather than explicit.

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 only implied: the counting framing suggests it is the right tool when an agent needs an aggregate rather than a listing, and 'points to the full-list route' hints at an alternative once the count exceeds 1,200. No sibling tool is named and no explicit when-not-to-use condition is given.

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 and openWorldHint, so the safety profile is covered. The description adds meaningful behavior beyond that: a 1-20 batch cap, pre-flight check-digit validation, and separate reporting of invalid versus unknown NPIs, which tells the agent partial failures are possible and distinguishable.

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 front-loaded sentences covering what is fetched, from where, how many, and how errors are handled. No filler; 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 a one-parameter read tool with annotations covering read-only and open-world access, this is nearly complete — it even lists the return fields in lieu of an output schema and explains error reporting. Only the NPI string format and per-item versus whole-batch failure semantics are left unstated.

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?

With a single parameter at 0% schema description coverage, the description compensates: it establishes that 'npis' is a batch of NPI numbers and that the 1-20 cardinality is enforced, mirroring the schema's minItems/maxItems. It stops short of stating the NPI digit format or whether the array is all-or-nothing.

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 (Fetch), resource (providers), keying (by NPI number), source (live CMS NPI Registry) and enumerates returned fields. This implicitly separates it from search_providers and count_by_specialty, but no sibling is named, so the differentiation is inferred rather than stated.

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 'by NPI number' framing implies this is the direct-lookup path versus search_providers, and the mention of check-digit validation hints at a relationship with validate_npi. However, there is no explicit when-to-use/when-not statement or named alternative.

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 and openWorldHint, and the description adds useful context the annotations can't convey: the 50-row return cap, the 1,200-result count ceiling, and the CMS rejection of state-only queries. It doesn't mention the skip/limit pagination semantics, which it could have.

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 dense sentences, front-loaded with the searchable fields and followed by the constraint and the return behavior. The trailing marketing URL is the only element that doesn't serve the invocation decision.

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 10-parameter, no-output-schema tool, the description covers what's searchable, what's required, what comes back, and the result ceiling — enough to call it correctly. The unreachable gap is the entity/limit/skip semantics, which neither the schema nor the description explains.

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 30%, so the description has to carry weight. It does clarify specialty format (taxonomy description as the registry writes it), state (2 letters) and ZIP, but leaves entity, limit and skip entirely to the schema, which is sparse. Partial compensation only.

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 ('Search the live NPI Registry') and enumerates the searchable fields, so the agent knows exactly what matching surface it gets. It doesn't explicitly name the sibling tools (lookup_npi, validate_npi, count_by_specialty), but 'search' vs 'lookup'/'validate' is naturally distinguishable.

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?

Gives a concrete precondition — at least one of name, organization, specialty, city or ZIP — and explains why (CMS refuses a state-only query). It also points to an alternative for full lists beyond the 50-row window, though it never says when to prefer lookup_npi or validate_npi.

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 and openWorldHint=false; the description reinforces the offline nature and adds substantive detail about what the check actually computes (Luhn check digit with prefix 80840) plus a clear negative capability statement. It stops short of describing the response shape or how failures are reported per item.

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, zero filler, with the core operation stated first and the limitation/alternative second. Every clause 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?

For a single-parameter validator with no output schema, the description covers what is validated, the input constraints, and the scope boundary against lookup_npi. The only gap is how per-item results or invalid inputs are returned, which the agent must discover by calling.

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 0%, so the description must carry the burden, and it does: it defines the expected format (10 digits, Luhn-valid, prefix 80840) and the batch limit of 50, which the schema only encodes as maxItems without explaining the underlying constraint. It does not clarify error behavior for malformed entries.

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 ('Offline check of ... NPI numbers') and specifies exactly what is checked: 10 digits, Luhn check digit, prefix 80840. This is clearly distinguishable from lookup_npi, which it names.

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 states the limitation ('Does not call CMS, so it cannot say whether the number is issued') and routes the agent to the correct alternative ('use lookup_npi for that'). When-to-use and when-not-to-use are both covered.

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