Handelsregister

Extract text of a filing document (AT)

get_document_text

Read-onlyIdempotent

Beispiel: „Was steht im Lagebericht des letzten Jahresabschlusses?“

Extracted text of ONE Austrian filing document, by its document key. Returns a WINDOW of the text, pageable via offset. Read-only.

    Parameters:
    - doc_key (required): the document_ref from list_documents (an Austrian filing key).
    - max_chars (optional, default 40000, clamped 1000-120000): size of ONE window.
    - offset (optional, default 0): character position the window starts at. To read a long
      filing, call again with offset = the previous response's ``next_offset`` until
      ``has_more`` is false; ``chars`` is the document's total length. Without offset the tail
      of a filing -- where the Anhang sits -- is unreachable at any cap.

    Returns {doc_key, text, chars, offset, returned_chars, next_offset, has_more, ...} with
    the filing's Stichtag for citation. ``attachments`` lists the documents embedded in the
    filing (Anhang, Lagebericht, Bestaetigungsvermerk) with their page count and whether their
    text could be extracted -- a scanned Anhang says so instead of answering empty, and when
    nothing can be extracted ``note`` explains why. Austria only today. Use list_documents to
    discover the key, get_document for the original artifact.

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": {
      "doc_key": "<doc_key>"
    },
    "name": "get_document_text"
  }
}

Input Schema

Name	Required	Description	Default
`offset`	No
`doc_key`	Yes
`max_chars`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 4, 2026

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "title": "Offset",
+  "type": "integer"
+}

AddedOct 11, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: pagination loop semantics (next_offset until has_more is false), the chars total, the 1000-120000 clamp on max_chars, and the consequence of omitting offset (the Anhang tail becomes unreachable). It also discloses failure behavior -- scanned attachments are reported rather than returning empty, and a note explains unextractable content.

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?

Well structured and front-loaded with an explicit Parameters block and a Returns block, so an agent can scan it quickly. Slightly over-long for the payload -- the opening German example sentence is atmospheric rather than operational, and the offset rationale is stated twice.

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?

Although an output schema exists, the description still flags the high-value return fields an agent needs for citation and paging (Stichtag, next_offset, has_more, chars, attachments with page counts and extraction status). For a paginated extraction tool with scan-related failure modes, nothing an agent needs in order to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry all parameter meaning, and it does: doc_key is tied to document_ref from list_documents, max_chars gets its default and its clamp range, and offset gets its default plus the exact recipe for advancing it from the previous response's next_offset. This is meaning no bare integer schema could convey.

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?

States a specific verb and resource ('Extracted text of ONE Austrian filing document, by its document key') plus the crucial scope constraint that it returns a paginated WINDOW rather than the whole document. It explicitly separates itself from the sibling list_documents (key discovery) and get_document (original artifact).

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?

Names the alternatives and the condition selecting them: use list_documents to discover the key, get_document for the original artifact. It also constrains applicability ('Austria only today') and provides a concrete motivating question in German to anchor when this tool is the right one.

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

All Handelsregister tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.