Skip to main content
Glama

Build a longlist of companies

longlists_find
Read-onlyIdempotent

Companies that fit a brief, in any country: from its register where Conecto reads one that lists industries (Conecto's index of its operating companies, or the register live around a point), and from the businesses on the map everywhere else (Overture Maps, and OpenStreetMap daily in Germany). Give the industries as NACE codes and, as the brief needs, headcount and revenue ranges, a point and radius, family-run or part of a group, and the business model in words; each company comes back scored out of 100 with its reasons and its facts, best first. What a source doesn't give earns half marks and says so, and a business from the map has its industry inferred from its listing. Read a register company further with companies_get and companies_financials. Costs $0.02 per company returned; nothing if none are found.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "industries": "<industries>"
    },
    "name": "longlists_find"
  }
}

Input Schema

NameRequiredDescriptionDefault
nearNoCompanies with a site within km of a point: 500 km at most, and 50 in France, whose register measures it.
limitNo
excludeNoCompany ids to leave out, like the ones already contacted.
countriesNoThe countries to search, as ISO codes ("DE", "BR") or names ("Germany", "Brasil"). Any country works: one whose register Conecto reads comes from it, every other from the businesses on the map (Overture Maps, and OpenStreetMap daily in Germany). Left out: the registers Conecto reads.
employeesNoHeadcount range, e.g. {"min": 20, "max": 199}.
ownershipNoindependent: no company leads it; group: part of a group.
industriesYesNACE Rev. 2 codes: a division (28), a group (28.9) or a class (28.93). Norway and newer Finnish filings are on NACE Rev. 2.1, searched under what each code became.
revenue_eurNoRevenue range in euros (France publishes revenue; elsewhere it counts as unknown).
business_modelNoWhat the companies do, in words a register might use, in English or the country's language ("combi ovens for restaurants, storkjøkken"). It ranks within the industries given: Norway by the purpose companies registered, by meaning; elsewhere by the words of their names, map listings and industries, so give the narrowest class.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral detail: scoring out of 100 with reasons and facts, best-first ordering, half marks for missing source data, industry inference for map businesses, and per-company pricing. These are traits an agent could not infer from the structured fields.

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

Conciseness2/5

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

The core purpose is front-loaded, but the body is a dense run-on with nested clauses ('from its register where Conecto reads one that lists industries ... and from the businesses on the map everywhere else') that is hard to parse. Several clauses restate source/ranking details already covered in the schema.

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?

For a 9-parameter open-world search with no output schema, the description covers return shape (scored companies with reasons and facts, best first), data-source caveats, pricing, and follow-up tools. What remains thin is an explicit statement of defaults/limits and how to iterate, but the essentials for correct invocation are present.

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 89%, so parameters are already well documented. The description restates the main filters (NACE codes, headcount/revenue ranges, point and radius, ownership, business model in words) but adds little syntax or constraint detail beyond what the schema carries; the ranking-hint for business_model largely duplicates the schema text.

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

Purpose4/5

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

The description clearly states the resource and outcome: companies matching a brief in any country, scored out of 100 and ordered best-first, drawn from registers or map data. It names concrete companion tools (companies_get, companies_financials) for follow-up, though it does not explicitly differentiate itself from near-siblings like companies_search or prospects_find.

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

Usage Guidelines3/5

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

Usage context is implied by 'companies that fit a brief' and by the follow-up routing to companies_get/companies_financials, but there is no explicit when-to-use-this-vs-alternatives guidance against companies_search, companies_estimate, or prospects_find. The cost note ('$0.02 per company returned; nothing if none are found') adds practical decision value.

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