Skip to main content
Glama

Find businesses in an area by ownership

find_businesses
Read-onlyIdempotent

List dentists, eye care practices, vets, dermatology or GI practices in a ZIP code, city or state, optionally filtered by ownership label. With industry "brand", list consumer brands instead (no location needed), filtered by label and by words in the brand, owner, backer or category (name), e.g. pet food brands with no known PE ties. Covers requests like "dentists in Plano, TX with no PE ties" (label=no_known_pe_ties) or "PE-backed eye doctors in 75024" (label=pe_backed,lender_owned). Labels: pe_backed, lender_owned (PE-backed, now lender-controlled), corporate_owned (not PE, owned by a company), health_system_owned, group_practice (owned by its dentists/doctors, no outside investor), vc_backed, no_known_pe_ties, unconfirmed, not_labeled; aliases pe and no_pe. Returns counts by label for the area, total, a page of results (limit up to 100, then next_offset) with each one's label wording and source, and the coverage note. Dental and eye care cover every NPI-registered practice; vet, derm and GI list only the tracked groups' locations. Some listings come from clinicians' individual NPI records and aren't confirmed open.

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_businesses"
  }
}

Input Schema

NameRequiredDescriptionDefault
zipNo5-digit ZIP code.
cityNo
nameNoOnly businesses whose name contains these words. For brands, words in the brand, owner, backer or category (e.g. "pet food", "Sycamore Partners").
labelNoOne or more labels, comma-separated, e.g. "no_known_pe_ties" or "pe_backed,lender_owned".
limitNoResults per page, default 20.
stateNoTwo-letter state code or state name. Needed with city unless the city name is unique.
offsetNoStart of the page (use next_offset).
industryNodental (default), eye, vet, derm, gi, or brand (consumer brands).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / industry / description
      Previous value: -"dental (default), eye, vet, derm or gi."New value: +"dental (default), eye, vet, derm, gi, or brand (consumer brands)."
    • changedInput schema / properties / industry / enum
      Previous value: -[
      -  "dental",
      -  "eye",
      -  "vet",
      -  "derm",
      -  "gi"
      -]New value: +[
      +  "dental",
      +  "eye",
      +  "vet",
      +  "derm",
      +  "gi",
      +  "brand"
      +]
    • changedInput schema / properties / name / description
      Previous value: -"Only businesses whose name contains these words."New value: +"Only businesses whose name contains these words. For brands, words in the brand, owner, backer or category (e.g. \"pet food\", \"Sycamore Partners\")."
  2. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds real context beyond them: partial coverage by vertical (dental/eye = all NPI-registered practices; vet/derm/GI = tracked groups only) and a data-quality caveat that some listings come from individual clinician NPI records and may not be confirmed open. That is useful, but it does not discuss rate limits or auth, so it sits at a solid middle score.

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 core purpose and the two variants, and the long label enumeration is genuinely necessary information rather than filler. The middle section is dense and runs together (mode switch, examples, label list) making it harder to scan than it could be, but almost every sentence carries operational value.

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 correctly takes on the return shape: counts by label, total, a page up to 100 with next_offset, per-result label wording and source, and the coverage note. It also discloses the data-quality caveat. The remaining gap is what happens for non-brand industries when no location is given, which an agent could plausibly get wrong.

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 88%, so the baseline is 3, but the description meaningfully exceeds it by enumerating and defining every label value (pe_backed, lender_owned, corporate_owned, health_system_owned, group_practice, vc_backed, no_known_pe_ties, unconfirmed, not_labeled, plus pe/no_pe aliases) that the schema only gestures at, and by explaining how name behaves in brand mode. It does not clarify location-combination rules or the default when no location is supplied.

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 concrete verb and resource set (list dentists, eye care, vets, derm, GI practices) scoped to a ZIP/city/state, plus a second explicit mode (industry="brand" for consumer brands). The scope is narrow enough that an agent can tell it apart from a single-entity sibling like lookup_business without opening the 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 concrete request shapes ('dentists in Plano, TX with no PE ties', 'PE-backed eye doctors in 75024') that show which label to use for which intent, and states that brand mode needs no location. It stops short of naming when to switch to get_group or lookup_business for detail on a single result, so the routing is implied rather than explicit.

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