Skip to main content
Glama

Handelsregister

by io.github.jkbngb

Export companies to CSV (AT + DE)

export_companies_csv
Read-only

Export a matched company set as downloadable CSV files (lead lists). Read-only over company data; each call writes new short-lived export files (auto-deleted after ~1 day).

    Parameters:
    - filters (optional): EXACTLY the same unified filters as search_companies.
    - sort (optional): same as search_companies (applies where the country supports
      the field).
    - max_rows (optional, default 1000, max 10000): per-country row ceiling.
    - country (optional, default "all"): "AT" | "DE" | "all".

    Returns {countries: {<code>: {download_url, rows, columns, ...}}, notices}. ONE
    CSV per country (semicolon-separated, UTF-8 BOM, Excel-ready): each register
    exports its own column set - DE files have no financial columns yet (blank would
    wrongly read as zero). Download links are signed and valid ~60 minutes. A filter a
    country does not support excludes that country with a notice, like
    search_companies. For browsing/ranking on screen use search_companies instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNo
countryNoall
filtersNo
max_rowsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.7/5.0
Behavior5/5

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

The description goes well beyond the annotations: it discloses that each call writes short-lived export files, auto-deletes them, provides signed download links valid for ~60 minutes, produces one CSV per country, and notes that DE files lack financial columns. It also explains the semantics only during prep instead of adding a misleading read_only hint. This is robust behavioral disclosure.

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?

Despite being detailed, the description is well-structured: it opens with the clear purpose, labels its main operational restrictions, lists parameters briefly, then describes return structure and usage boundaries. Every sentence adds meaningful information about behavior or an edge case; there is no padding.

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

Completeness5/5

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

Given the complexity of creating country-specific CSV exports with transient files, the description covers the full operational surface: output shape, row limit, defaults, file format, and per-country column differences. The annotations and structured schema add further context, making the description complete enough for an agent to invoke correctly.

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 description coverage is 0%, so the description needs to be the sole parameter explainer. It succeeds for all four parameters: filters (exact same as search_companies), sort, max_rows (default 1000/max), and country (AT|DE|all). It does not enumerate the filter fields here, instead referring to a sibling schema, but that is a reasonable pointer for a large unified filter object.

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 uses a specific verb ('Export') with a well-defined resource ('matched company set' as CSV files) and explicitly names the AT + DE scope and the downloadable CSV output. It also distinguishes itself from screen-browsing search tools, so an agent can tell this is the export/lead-list tool.

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?

The description explicitly says 'For browsing/ranking on screen use search_companies instead', which is a clear alternative. It also clarifies that filters and sort are intentionally shared with search_companies, so use of this tool is well-routed. It could go further by naming other sibling conditions, but the guidance is strong.

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

All Handelsregister toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.8/5.0
Disambiguation4/5

Each tool has a distinct primary purpose, with clear pointers to the right tool for the job. The main possible confusion is between describe_fields/get_coverage and search_companies/search_person, but the descriptions actively disambiguate those boundaries.

Naming Consistency5/5

All tool names follow a consistent lowercase snake_case verb_noun pattern: describe_fields, export_companies_csv, get_company_details, list_events, search_companies. Even ping fits the predictable style as a simple liveness verb.

Tool Count5/5

Eleven tools is well-scoped for a unified company-register facade. Each tool covers a distinct part of the surface: schema, coverage, search, detail, persons, peers, events, statistics, export, and diagnostics.

Completeness5/5

The read-only domain is covered thoroughly: lookup, detail, person search, similarity, event feeds, aggregate stats, and export all exist. Unsupported country-specific features are handled with notices and coverage metadata rather than missing tooling.

Resources