Skip to main content
Glama

Lead Strategist: Danish CVR company data

Search Danish companies

search_companies
Read-onlyIdempotent

Search Danish companies in the CVR read model (read-only). Filters include industry, size, municipality (kommune), city/postnummer and region. Prefer exclude_reklamebeskyttelse=true for marketing leads.

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": "search_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoPostal town (postdistrikt) as a prefix match, or a 4-digit postal code, e.g. 'Aarhus' (matches 'Aarhus C' and 'Aarhus N') or '8000'.
limitNoNumber of companies to return (1 to 50), e.g. 20. Default 20.
offsetNoNumber of results to skip, for paging, e.g. 20 for page 2 with limit 20. Default 0.
regionNoDanish region, e.g. 'Midtjylland'. One of Hovedstaden, Sjælland, Syddanmark, Midtjylland, Nordjylland ('Region ' prefix optional).
max_revenueNoMaximum revenue in DKK from the latest annual report, e.g. 50000000 for 50 million DKK.
min_revenueNoMinimum revenue (omsætning) in DKK from the latest annual report, e.g. 10000000 for 10 million DKK.
municipalityNoMunicipality (kommune) of the current CVR address, by name or code, e.g. 'Aarhus', 'Københavns Kommune' or '751'.
industry_codeNoExact Danish industry code (DB25/NACE, up to 6 digits), e.g. "621000" (computer programming).
max_employeesNoMaximum average number of employees from the latest annual report, e.g. 50.
min_employeesNoMinimum average number of employees from the latest annual report, e.g. 10.
status_containsNoCase-insensitive part of the CVR status (Danish), e.g. "normal" or "aktiv" for active companies, "konkurs" for bankruptcy.
industry_containsNoCase-insensitive text match on the industry name and secondary industries (Danish), e.g. "tømrer", "software" or "restaurant".
company_name_containsNoCase-insensitive part of the company name, e.g. "Novo" or "Carlsberg".
exclude_reklamebeskyttelseNoLeave out companies with reklamebeskyttelse (marketing protection, may not be contacted for marketing). Default true; set false only for research, not outreach.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / company_name_contains / maxLength
      Previous value: -120New value: +100
    • changedInput schema / properties / industry_contains / maxLength
      Previous value: -120New value: +100
    • changedInput schema / properties / status_contains / maxLength
      Previous value: -80New value: +50
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

The '(read-only)' parenthetical merely repeats readOnlyHint and earns no credit since annotations already declare readOnly, idempotent, and non-destructive behavior. The marketing-protection note is a useful compliance trait, but it is already spelled out in the exclude_reklamebeskyttelse schema description, and the tool never says what a result looks like or how paging behaves.

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

Conciseness5/5

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

Two short sentences with zero filler: source and read-only status first, filter surface second, actionable default last. Everything is front-loaded and nothing repeats.

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 14 optional parameters, 100% schema coverage and full annotations, the description covers selection context well, but with no output schema it never indicates what company fields are returned or roughly how large a result set is, which an agent needs to plan paging and follow-up calls.

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%, so the schema already documents every filter including examples, defaults and bounds. The description only gestures at filter families ('industry, size, municipality, city/postnummer and region') and omits name, revenue, employees and status filters, adding marginal meaning over the schema.

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?

States a specific verb+resource ('Search Danish companies') and names the data source (CVR read model), so the agent knows exactly what entity is being queried. It does not explicitly distinguish itself from the sibling get_company, which targets a single company, leaving that inference to the agent.

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?

The only guidance is 'Prefer exclude_reklamebeskyttelse=true for marketing leads,' which is parameter advice rather than tool-selection guidance. Nothing says when to use this search vs. get_company or recommend_leads, so the agent must infer that this is the filtered-list entry point.

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