Skip to main content
Glama
Tiwas

Firmaradar

Search Companies

firmaradar_search_companies
Read-onlyIdempotent

Find Norwegian companies by name, NACE, location, status, employees, revenue, and founding date. Returns candidate organization numbers to investigate further.

Instructions

Search Norwegian companies with filters (name, NACE, location, status, employees, revenue range, founding date). Returns paginated list of candidate orgnr to investigate further. Use when you have a description and need to find matching companies; use get_company once you have a specific orgnr. Revenue filtering excludes companies with no reported NOK revenue figure — see min_omsetning_nok. Backed by the official Norwegian company register (BRREG). Each hit includes a canonical Firmaradar url and the fields that matched the requested filters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFree-text search across company names.
naceNoNACE code or prefix. Norwegian BRREG uses 5-digit SN2007 codes internally (e.g. '56.110' for restaurants, '47.111' for grocery stores). Any prefix works: '47' matches all retail (2-digit), '47.1' matches food/beverage retail (3-digit), '47.11' matches grocery stores (4-digit), '47.111' is the most specific (5-digit). If a 4-digit code yields no results, try appending '0' for the 5-digit form (e.g. '56.110' instead of '56.10').
fylkeNoNorwegian fylkenummer — EXACTLY 2 digits, zero-padded. Examples: '03' = Oslo, '11' = Rogaland, '15' = Møre og Romsdal. Fylke-NAMES are NOT accepted — translate first.
limitNo
cursorNoOpaque pagination cursor from previous call.
statusNoFilter on company status.
kommuneNoNorwegian kommunenummer — EXACTLY 4 digits, zero-padded. Examples: '0301' = Oslo, '4601' = Bergen, '5001' = Trondheim, '1103' = Stavanger. Kommune-NAMES are NOT accepted — translate the name to kommunenummer first.
max_ansatteNo
min_ansatteNo
stiftet_forNoISO 8601 date — only companies founded on/before.
stiftet_etterNoISO 8601 date — only companies founded on/after.
max_omsetning_nokNoMaximum annual revenue (driftsinntekter) in NOK — same source and same exclusion rule as min_omsetning_nok.
min_omsetning_nokNoMinimum annual revenue (driftsinntekter) in NOK, from the company's own accounts (not consolidated/group figures), latest year with a reported figure. NOTE: companies with no reported revenue are EXCLUDED from the results when this filter is set, as are accounts reported in a foreign currency. Must be combined with at least one of q/nace/kommune.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes
next_cursorNo
total_countNo
omsetning_filter_noteNoSet only when a revenue range was requested: explains that companies without a reported NOK revenue figure were excluded, so an empty result may mean missing accounts rather than no matching companies.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.2
    • addedInput schema / properties / max_omsetning_nok / description
      Added value: +"Maximum annual revenue (driftsinntekter) in NOK — same source and same exclusion rule as min_omsetning_nok."
    • addedInput schema / properties / min_omsetning_nok / description
      Added value: +"Minimum annual revenue (driftsinntekter) in NOK, from the company's own accounts (not consolidated/group figures), latest year with a reported figure. NOTE: companies with no reported revenue are EXCLUDED from the results when this filter is set, as are accounts reported in a foreign currency. Must be combined with at least one of q/nace/kommune."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$defs": {
      +    "CompanyHit": {
      +      "properties": {
      +        "antall_ansatte": {
      +          "anyOf": [
      +            {
      +              "type": "integer"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "title": "Antall Ansatte"
      +        },
      +        "kommune": {
      +          "anyOf": [
      +            {
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "title": "Kommune"
      +        },
      +        "naeringskode": {
      +          "anyOf": [
      +            {
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "title": "Naeringskode"
      +        },
      +        "navn": {
      +          "title": "Navn",
      +          "type": "string"
      +        },
      +        "organisasjonsform": {
      +          "anyOf": [
      +            {
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "title": "Organisasjonsform"
      +        },
      +        "orgnr": {
      +          "title": "Orgnr",
      +          "type": "string"
      +        },
      +        "status": {
      +          "anyOf": [
      +            {
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "title": "Status"
      +        },
      +        "stiftelsesdato": {
      +          "anyOf": [
      +            {
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "title": "Stiftelsesdato"
      +        }
      +      },
      +      "required": [
      +        "orgnr",
      +        "navn"
      +      ],
      +      "title": "CompanyHit",
      +      "type": "object"
      +    }
      +  },
      +  "properties": {
      +    "items": {
      +      "items": {
      +        "$ref": "#/$defs/CompanyHit"
      +      },
      +      "title": "Items",
      +      "type": "array"
      +    },
      +    "next_cursor": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Next Cursor"
      +    },
      +    "omsetning_filter_note": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "description": "Set only when a revenue range was requested: explains that companies without a reported NOK revenue figure were excluded, so an empty result may mean missing accounts rather than no matching companies.",
      +      "title": "Omsetning Filter Note"
      +    },
      +    "total_count": {
      +      "anyOf": [
      +        {
      +          "type": "integer"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Total Count"
      +    }
      +  },
      +  "required": [
      +    "items"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond those annotations: pagination, the revenue exclusion rule, the BRREG data source, and that each hit includes a canonical URL and matching fields. This goes beyond the safety profile annotations provide.

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?

The description is composed of five dense sentences, each carrying unique information. It is front-loaded with purpose, then results, usage, caveat, and data source. While not overly long, a few details could be trimmed without loss, so not a perfect 5.

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 13-parameter search tool with an output schema and detailed annotations, the description covers purpose, usage, a key exclusion behavior, data source, and return value highlights. It does not repeat return-value structure (thanks to output schema) but is sufficiently complete for an agent to select and invoke the tool.

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 77%, and the schema itself contains detailed parameter descriptions (e.g., NACE prefix matching, exact fylke format, min_omsetning exclusion rule). The tool description adds little new parameter-level meaning beyond referencing the revenue exclusion caveat already present in the schema, so baseline 3 is appropriate.

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?

The description begins with 'Search Norwegian companies with filters' which is a specific verb+resource+scope. It clearly distinguishes itself from sibling tools by stating 'use `get_company` once you have a specific orgnr' and describing the result as 'paginated list of candidate orgnr to investigate further.'

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?

Explicit guidance is provided: 'Use when you have a description and need to find matching companies; use `get_company` once you have a specific orgnr.' This also serves as a when-not instruction, naming the alternative tool. Additionally, the revenue filter caveat tells the agent when results will be excluded.

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