Skip to main content
Glama

NS Pros MCP Gateway

npi-registry__classify_row

Cheap categorization: given a company and a list of candidate labels, decide which labels apply, the most common GTM/AI usage shape (tagging a list by industry, ICP fit, etc.), one small model call. Same evidence contract as research_row: each label comes back {label, applies, evidence_url, quote, status: found|inferred|not_established}, "found" only when the model's quote is independently verified as a verbatim substring of the text used. Pass text directly (cheapest, no fetch) or entity.domain

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "entity": {
        "name": "Stripe",
        "domain": "stripe.com"
      },
      "labels": [
        "healthcare",
        "fintech",
        "logistics"
      ]
    },
    "name": "npi-registry__classify_row"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoText to classify directly (a description, a page you already fetched, etc.), cheapest path, skips any fetch.
entityYesThe row/company to classify. At least one of name/domain required.
labelsYesCandidate labels to test, 2-30 strings, e.g. ["healthcare","fintech","logistics"].

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses the cost profile ('cheap', one small model call), the per-label return shape with status enum found|inferred|not_established, and the verification rule that 'found' requires a verbatim substring match. It also discloses the side effect that the homepage is fetched only when text is absent. Remaining gaps are failure modes and any limits on model calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose and cheapest invocation path, then the output contract. It is dense with comma splices and a trailing stray quotation mark, but nearly every clause (cost, fetch behavior, evidence contract) earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the important things for a three-parameter, nested, output-schema-less tool: input precedence, cost, and return shape. It stops short of explaining behavior when neither usable text nor domain is supplied, or what happens with invalid or out-of-range label counts beyond the schema's 2-30 hint.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by explaining text is the 'cheapest path, skips any fetch' and that entity.domain triggers a homepage fetch only when text is not provided — a precedence rule the schema does not state. The labels parameter semantics are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: given a company and candidate labels, decide which labels apply. It also frames the tool relative to a sibling by saying it is 'cheap categorization' with 'one small model call' and the same evidence contract as research_row, so an agent can tell it apart from the heavier research tool 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.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the canonical usage shape explicitly (tagging a list by industry, ICP fit, etc.) and the cost-based selection rationale ('cheap', 'one small model call'), which implicitly steers agents away from deep research for simple tagging. It does not state explicit exclusions or when a heavier sibling should be preferred instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.