Skip to main content
Glama

Find NAICS codes

find_naics
Read-onlyIdempotent

Which NAICS codes a kind of business falls under, and how many companies the database holds under each: the step before find_companies when a request describes businesses in words ("substation construction", "foundation drilling", "dental labs"). Give every kind the request names in one call. Each is matched against the Census Bureau's own index of what is filed under every code, and comes back with the codes that fit, the index lines that matched, and each code's count of companies. Also checks codes you already have in mind. Then search every code you choose in one find_companies call.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_naics"
  }
}

Input Schema

NameRequiredDescriptionDefault
codesNoCodes you already have in mind, to check before searching: each comes back with its title, what the Census Bureau files under it, and how many companies the database holds.
describeNoKinds of business in plain words, one an item, as many as the request names: ["substation construction", "foundation drilling", "data center construction"]. Each is matched against the Census Bureau's index of what is filed under every NAICS code.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), so the burden is lower. The description adds real behavioral context that annotations cannot: results include the fitted codes, the index lines that matched, and per-code company counts, and it names the matching basis (the Census Bureau's index of what is filed under each code). It stops short of saying what happens on no match or how results are ordered.

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?

Purpose is front-loaded and every sentence carries a distinct instruction: what it does, when to use it, batching, pre-checking, and the follow-up call. It is denser and more clause-heavy than needed in places (e.g. 'how many companies the database holds under each'), which costs a point but not comprehension.

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

Completeness4/5

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

With no output schema, the description does the necessary work of describing the return payload (matching codes, matched index lines, company counts). Together with the sibling hand-off and the schema's own 100% coverage, an agent has enough to call it correctly; edge behavior such as zero-match handling is the only notable omission.

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

Parameters3/5

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

Schema description coverage is 100% and both parameter descriptions already explain that codes come back with title, filing notes and company count, and that describe items are matched against the Census index. The description's parameter-relevant content ('Also checks codes you already have in mind', 'one an item') largely restates the schema, so baseline 3 applies rather than a bonus.

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?

Opens with a specific verb+resource: it returns which NAICS codes a kind of business falls under plus company counts per code. It also draws an explicit boundary against the sibling find_companies ('the step before find_companies'), so an agent can route between the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

States the triggering condition precisely — a request that describes businesses in words, with concrete examples ('substation construction', 'dental labs'). It gives batching guidance ('Give every kind the request names in one call'), covers the pre-check case for codes already known, and hands off to find_companies for the follow-up search.

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.

Resources