Skip to main content
Glama

Get RIS Document

ris_get_document
Read-onlyIdempotent

Fetch one RIS document’s full text or its rendition URLs, with explicit binding status and the amtssigniert authentic PDF surfaced wherever it exists. Address the document exactly one of two ways: document_number plus application (both copied verbatim from a ris_search_* or ris_lookup_citation result), or a document_url — a record’s own document_url or eli (an ELI or Dokument.wxe web view, read for the document it names without fetching the link), one of its content_urls, or, for a draft’s companion documents (Erläuterungen, Textgegenüberstellung, WFA, cover letter, annexes), a ris_search_drafts record’s materials[].url, which is the only route to them. format: markdown (default — the HTML rendition converted to markdown, or the PDF’s extracted text where a PDF is the only rendition), html (raw HTML rendition), xml (the RIS Nutzdaten XML), or urls_only (no fetch — every rendition URL, including the Authentisch PDF). Format availability varies by application and the tool degrades explicitly, never silently: consolidated law, gazettes, case law, drafts, and most sectoral collections carry full text; district and municipal promulgations and court rules (Bvb, GrA, KmGer) publish only the signed authentic PDF; party-transparency decisions and council minutes (Upts, Mrp) are PDF-only; the 1848–1940 imperial gazettes (BgblAlt) are metadata-only. Where a PDF is the only rendition — those PDF-only and authentic-PDF-only applications, and a draft companion filed with no html twin — markdown returns the text extracted from it (text_source: pdf, a "--- Page N of M ---" line before each page, a notice naming the PDF); for an authentic application the signed PDF stays the binding artifact to cite. html and xml there, every format on BgblAlt, and a PDF whose text cannot be extracted (a scan with no text layer — no OCR is performed — or an oversized, unreadable, or unreachable file) return a format_unavailable notice with the usable URL, not an error. Every result carries binding_status; only authentic (amtssigniert) publications are legally binding. This tool returns content, not fresh metadata — the metadata rides the search/lookup step that produced the document number. When the markdown text overflows the 40,000-byte budget the tool returns an outline (kind: outline) instead of truncating: the document’s §/Artikel/Anlage sections where it carries at least two such headings, otherwise contiguous byte windows named Part 1 of N … Part N of N covering the whole text and listed in document order. Re-call with sections:[…] naming outline entries to retrieve just those; a name matching nothing returns the outline again with a notice rather than the whole document. Windows are cut at line breaks, not at sentence or § boundaries, so one can open mid-sentence — read them in order and pull the neighbour when a passage straddles a cut. Raw html and xml renditions are never sliced: at or under the 40,000-byte budget they return whole; over it the result is kind: link — no text, truncated: true, the full byte_size, and content_urls, whose html or xml entry fetches the whole artifact in one GET. Every HTML rendition opens with a 40–70 KB stylesheet, so html practically always returns kind: link — read with markdown, parse with xml, and fetch content_urls.html for the authentic markup. Markdown drops the screen-reader expansions RIS ships alongside each abbreviated citation, keeping the visible citation form, and prints each Absatz, Ziffer, and litera under its own statutory label — (1a), 2., b) — with no generated list number in front; raw html/xml renditions are returned exactly as published.

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": "ris_get_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNomarkdown (default — the HTML rendition converted to markdown, or the text extracted from the PDF where a PDF is the document’s only rendition; the format for reading), html (raw HTML rendition), xml (RIS Nutzdaten schema), or urls_only (no fetch — all rendition URLs incl. the authentic PDF). html and xml over 40,000 bytes return kind: link with no text — nearly every html rendition does, since each carries a 40–70 KB stylesheet — so fetch content_urls.html or content_urls.xml for the whole artifact.markdown
sectionsNoEntry names to retrieve, each copied verbatim from a prior outline response (kind: outline) — §/Artikel/Anlage section names, or window names of the form "Part 2 of 6". Omit for the full document, which returns an outline instead when the markdown overflows the 40,000-byte budget. A name that matches no entry is never silently ignored: one naming a heading inside quoted replacement text (an amending act’s „…“ wording, which stays inside the entry quoting it) returns that heading’s passage with a notice naming the entry; otherwise a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched entries with a notice naming others to pick from. Applies to markdown only. html and xml are never sliced — the selector is ignored with a notice, and they return whole under the 40,000-byte budget and as kind: link over it; urls_only carries no text to select from.
applicationNoRIS application the document belongs to (e.g. BrKons, Dsk, BgblAuth) — copy verbatim from the same result. Required with document_number. Codes and coverage: ris_list_reference topic applications.
document_urlNoA link to one RIS document, passed exactly as a result returned it — the alternative to document_number + application. Accepted: a record’s own document_url or eli — an ELI or a Dokument.wxe web view on ris.bka.gv.at, www.ris.bka.gv.at, or ogd.ris.bka.gv.at, over https or http, read for the application and document number it names, so nothing is fetched from the link and the result is the document_number + application call’s; or a /Dokumente/… rendition URL on https://www.ris.bka.gv.at or https://ogd.ris.bka.gv.at from a result’s content_urls. Other RIS web views (GeltendeFassung, JudikaturEntscheidung, JudikaturRechtssaetze, VwghRechtssatzkette, VergEntscheidung) name a whole law or several documents and are rejected. Also the only way to read a draft’s companion documents: pass a ris_search_drafts record’s materials[].url (the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Every companion filename RIS publishes is accepted, whichever shape it carries. The URL’s own extension is only checked against the rendition extensions RIS uses and is then discarded — format selects which rendition is returned, for a companion exactly as for a main document. A filename that is neither this document’s own rendition nor one of its companions is rejected; companion filenames cannot be composed by hand, so copy one verbatim.
document_numberNoTechnical RIS document number (Technisch.ID), e.g. NOR40262691, JJT_…, BGBLA_2026_II_171 — copy verbatim from a ris_search_* or ris_lookup_citation result. Requires application; mutually exclusive with document_url.

Output Schema

NameRequiredDescriptionDefault
kindNofull — the complete response (document text, selected entries, or rendition URLs). outline — sections lists the retrievable entries instead of the text, either because the markdown overflowed the byte budget or because a sections:[…] selector matched nothing; re-call with sections:[…] naming entries from it. link — an html or xml rendition over the 40,000-byte budget: no text, only byte_size and content_urls, whose entry for the requested format fetches the whole artifact in one GET; re-call with format: markdown to read it.
textNoThe document text in the requested format. Markdown writes every image as an absolute URL on the content host. For markdown on a document whose only rendition is a PDF, or whose html rendition carries only page images, the text extracted from that PDF, a "--- Page N of M ---" line before each page (text_source: pdf); where that PDF has no text, the page images instead (text_source: html, the notice says so). Absent for urls_only, when no text could be returned (see the notice), for an outline (kind: outline), and for an html or xml rendition over the 40,000-byte budget (kind: link).
errorNoPresent when the call failed. Absent on success.
formatNoThe format served — echoes the requested format.
noticeNoPresent when the text was extracted from a PDF (names the PDF and what extraction loses, ahead of any other notice below), when an html rendition carries only page images and its PDF has no extractable text (gives the image count, names content_urls.pdf and why, ahead of any other notice below), when the requested text format is unavailable or a PDF’s text could not be extracted (names why and the usable URL, and that a sections:[…] selector was ignored), when the document overflowed to a section outline (names how to retrieve sections), when an html or xml rendition overflowed to a link (names content_urls.<format> and format: markdown), or when a sections:[…] entry matched no section or was ignored (names the unmatched entries).
sectionsNoPresent when kind = outline: the document’s addressable entries, each with its UTF-8 byte size — §/Artikel/Anlage sections listed largest first, or, when the markdown carries no such headings, Part n of N byte windows listed in document order and summing to byte_size. Copy names into the sections input verbatim to retrieve them; naming several in one call returns their text concatenated in document order, with nothing inserted between them.
byte_sizeNoFull UTF-8 byte size of the document text. Present when text was fetched — for an overflowed document (kind: outline) or an over-budget html/xml rendition (kind: link) this reports the full text’s size, not the returned payload’s.
truncatedNoPresent and true when the full text isn’t inline. kind: outline — the markdown overflowed the byte budget or a sections:[…] selector matched nothing (the notice names which); retrieve entries via the sections input. kind: link — an html or xml rendition overflowed the budget; fetch content_urls.html or content_urls.xml for the whole artifact, or re-call with format: markdown.
applicationNoRIS application the document belongs to (echoed).
text_sourceNoWhere the markdown text (or the outline it was cut from) came from: html — converted from the HTML rendition; pdf — extracted from the PDF, the document’s only readable rendition, so line breaks, tables, and footnotes may be out of order (the notice names the PDF). Present on every markdown result that carries text or sections.
content_urlsNoConstructed rendition URLs. Empty for authentic-PDF-only (Bvb/GrA/KmGer) and metadata-only (BgblAlt) applications — see authentic_pdf_url and the notice. For a companion document (a draft’s Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex) these are the companion’s own XML/HTML/PDF, not the parent document’s — constructed rather than read back from RIS, so for the roughly one companion in eight that RIS files as a PDF only, xml and html return 404 and pdf is the one that resolves.
binding_statusNoLegal binding status: authentic (amtssigniert, legally binding), consolidated_informational (consolidated view — not binding), historical_record (superseded/pre-e-Recht promulgation), decision (court/tribunal ruling), preparatory (draft/bill/minutes), administrative_directive (binds the administration, not citizens), or translation (unofficial English).
document_numberNoTechnical RIS document number (echoed).
authentic_pdf_urlNoThe amtssigniert authentic PDF (.pdfsig, Authentisch DataType) — the legally binding artifact — where the application publishes one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / document_url / description
      Previous value: -"A /Dokumente/… rendition URL on https://www.ris.bka.gv.at or https://ogd.ris.bka.gv.at, passed exactly as a result’s content_urls returned it — the alternative to document_number + application. Also the only way to read a draft’s companion documents: pass a ris_search_drafts record’s materials[].url (the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Every companion filename RIS publishes is accepted, whichever shape it carries. The URL’s own extension is only checked against the rendition extensions RIS uses and is then discarded — format selects which rendition is returned, for a companion exactly as for a main document. A filename that is neither this document’s own rendition nor one of its companions is rejected; companion filenames cannot be composed by hand, so copy one verbatim."New value: +"A link to one RIS document, passed exactly as a result returned it — the alternative to document_number + application. Accepted: a record’s own document_url or eli — an ELI or a Dokument.wxe web view on ris.bka.gv.at, www.ris.bka.gv.at, or ogd.ris.bka.gv.at, over https or http, read for the application and document number it names, so nothing is fetched from the link and the result is the document_number + application call’s; or a /Dokumente/… rendition URL on https://www.ris.bka.gv.at or https://ogd.ris.bka.gv.at from a result’s content_urls. Other RIS web views (GeltendeFassung, JudikaturEntscheidung, JudikaturRechtssaetze, VwghRechtssatzkette, VergEntscheidung) name a whole law or several documents and are rejected. Also the only way to read a draft’s companion documents: pass a ris_search_drafts record’s materials[].url (the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Every companion filename RIS publishes is accepted, whichever shape it carries. The URL’s own extension is only checked against the rendition extensions RIS uses and is then discarded — format selects which rendition is returned, for a companion exactly as for a main document. A filename that is neither this document’s own rendition nor one of its companions is rejected; companion filenames cannot be composed by hand, so copy one verbatim."
    • changedInput schema / properties / sections / description
      Previous value: -"Entry names to retrieve, each copied verbatim from a prior outline response (kind: outline) — §/Artikel/Anlage section names, or window names of the form \"Part 2 of 6\". Omit for the full document, which returns an outline instead when the markdown overflows the 40,000-byte budget. A name that matches no entry is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched entries with a notice naming others to pick from. Applies to markdown only. html and xml are never sliced — the selector is ignored with a notice, and they return whole under the 40,000-byte budget and as kind: link over it; urls_only carries no text to select from."New value: +"Entry names to retrieve, each copied verbatim from a prior outline response (kind: outline) — §/Artikel/Anlage section names, or window names of the form \"Part 2 of 6\". Omit for the full document, which returns an outline instead when the markdown overflows the 40,000-byte budget. A name that matches no entry is never silently ignored: one naming a heading inside quoted replacement text (an amending act’s „…“ wording, which stays inside the entry quoting it) returns that heading’s passage with a notice naming the entry; otherwise a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched entries with a notice naming others to pick from. Applies to markdown only. html and xml are never sliced — the selector is ignored with a notice, and they return whole under the 40,000-byte budget and as kind: link over it; urls_only carries no text to select from."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the origin + /Dokumente/ path-prefix allowlist (exactly https://www.ris.bka.gv.at and https://ogd.ris.bka.gv.at), its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. A PDF read for its text degrades to the format_unavailable notice instead. `content_host_blocked`: The configured RIS content host answered with a bot-check page (\"Security Check\") instead of the document — it refuses automated clients, so every read through it fails the same way. A PDF read for its text degrades to the format_unavailable notice instead. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. A PDF read for its text degrades to the format_unavailable notice instead. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url is an ELI or Dokument.wxe web view in a shape that names no one document (a work-level or unknown ELI layout, an Abfrage naming no application, a missing or repeated Dokumentnummer, a port other than the default or a scheme other than https or http), or a URL that fails the origin + /Dokumente/ path-prefix allowlist (exactly https://www.ris.bka.gv.at and https://ogd.ris.bka.gv.at), whose path segment is not a recognized RIS application, or whose trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. A PDF read for its text degrades to the format_unavailable notice instead. `content_host_blocked`: The configured RIS content host answered with a bot-check page (\"Security Check\") instead of the document — it refuses automated clients, so every read through it fails the same way. A PDF read for its text degrades to the format_unavailable notice instead. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. A PDF read for its text degrades to the format_unavailable notice instead. Other values are possible when a failure originates below the handler."
  2. Changed5 schema fields changed
    • changedInput schema / properties / format / description
      Previous value: -"markdown (default — the HTML rendition converted to markdown, and the format for reading), html (raw HTML rendition), xml (RIS Nutzdaten schema), or urls_only (no fetch — all rendition URLs incl. the authentic PDF). html and xml over 40,000 bytes return kind: link with no text — nearly every html rendition does, since each carries a 40–70 KB stylesheet — so fetch content_urls.html or content_urls.xml for the whole artifact."New value: +"markdown (default — the HTML rendition converted to markdown, or the text extracted from the PDF where a PDF is the document’s only rendition; the format for reading), html (raw HTML rendition), xml (RIS Nutzdaten schema), or urls_only (no fetch — all rendition URLs incl. the authentic PDF). html and xml over 40,000 bytes return kind: link with no text — nearly every html rendition does, since each carries a 40–70 KB stylesheet — so fetch content_urls.html or content_urls.xml for the whole artifact."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the origin + /Dokumente/ path-prefix allowlist (exactly https://www.ris.bka.gv.at and https://ogd.ris.bka.gv.at), its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. `content_host_blocked`: The configured RIS content host answered with a bot-check page (\"Security Check\") instead of the document — it refuses automated clients, so every read through it fails the same way. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the origin + /Dokumente/ path-prefix allowlist (exactly https://www.ris.bka.gv.at and https://ogd.ris.bka.gv.at), its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. A PDF read for its text degrades to the format_unavailable notice instead. `content_host_blocked`: The configured RIS content host answered with a bot-check page (\"Security Check\") instead of the document — it refuses automated clients, so every read through it fails the same way. A PDF read for its text degrades to the format_unavailable notice instead. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. A PDF read for its text degrades to the format_unavailable notice instead. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / notice / description
      Previous value: -"Present when the requested text format is unavailable for this application (names why and the usable URL), when the document overflowed to a section outline (names how to retrieve sections), when an html or xml rendition overflowed to a link (names content_urls.<format> and format: markdown), or when a sections:[…] entry matched no section or was ignored (names the unmatched entries)."New value: +"Present when the text was extracted from a PDF (names the PDF and what extraction loses, ahead of any other notice below), when an html rendition carries only page images and its PDF has no extractable text (gives the image count, names content_urls.pdf and why, ahead of any other notice below), when the requested text format is unavailable or a PDF’s text could not be extracted (names why and the usable URL, and that a sections:[…] selector was ignored), when the document overflowed to a section outline (names how to retrieve sections), when an html or xml rendition overflowed to a link (names content_urls.<format> and format: markdown), or when a sections:[…] entry matched no section or was ignored (names the unmatched entries)."
    • changedOutput schema / properties / text / description
      Previous value: -"The document text in the requested format. Absent for urls_only, when the application carries no text rendition (see the notice), for an outline (kind: outline), and for an html or xml rendition over the 40,000-byte budget (kind: link)."New value: +"The document text in the requested format. Markdown writes every image as an absolute URL on the content host. For markdown on a document whose only rendition is a PDF, or whose html rendition carries only page images, the text extracted from that PDF, a \"--- Page N of M ---\" line before each page (text_source: pdf); where that PDF has no text, the page images instead (text_source: html, the notice says so). Absent for urls_only, when no text could be returned (see the notice), for an outline (kind: outline), and for an html or xml rendition over the 40,000-byte budget (kind: link)."
    • addedOutput schema / properties / text_source
      Added value: +{
      +  "description": "Where the markdown text (or the outline it was cut from) came from: html — converted from the HTML rendition; pdf — extracted from the PDF, the document’s only readable rendition, so line breaks, tables, and footnotes may be out of order (the notice names the PDF). Present on every markdown result that carries text or sections.",
      +  "enum": [
      +    "html",
      +    "pdf"
      +  ],
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the origin + /Dokumente/ path-prefix allowlist (exactly https://www.ris.bka.gv.at and https://ogd.ris.bka.gv.at), its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the origin + /Dokumente/ path-prefix allowlist (exactly https://www.ris.bka.gv.at and https://ogd.ris.bka.gv.at), its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. `content_host_blocked`: The configured RIS content host answered with a bot-check page (\"Security Check\") instead of the document — it refuses automated clients, so every read through it fails the same way. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "invalid_addressing",
      -  "unsupported_url",
      -  "document_not_found",
      -  "upstream_error",
      -  "upstream_timeout"
      -]New value: +[
      +  "invalid_addressing",
      +  "unsupported_url",
      +  "document_not_found",
      +  "upstream_error",
      +  "content_host_blocked",
      +  "upstream_timeout"
      +]
  4. Changed10 schema fields changed
    • changedInput schema / properties / document_url / description
      Previous value: -"A https://www.ris.bka.gv.at/Dokumente/… rendition URL as returned in a result’s content_urls — the alternative to document_number + application. Also the only way to read a draft’s companion documents: pass a ris_search_drafts record’s materials[].url (the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Every companion filename RIS publishes is accepted, whichever shape it carries. The URL’s own extension is only checked against the rendition extensions RIS uses and is then discarded — format selects which rendition is returned, for a companion exactly as for a main document. A filename that is neither this document’s own rendition nor one of its companions is rejected; companion filenames cannot be composed by hand, so copy one verbatim."New value: +"A /Dokumente/… rendition URL on https://www.ris.bka.gv.at or https://ogd.ris.bka.gv.at, passed exactly as a result’s content_urls returned it — the alternative to document_number + application. Also the only way to read a draft’s companion documents: pass a ris_search_drafts record’s materials[].url (the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Every companion filename RIS publishes is accepted, whichever shape it carries. The URL’s own extension is only checked against the rendition extensions RIS uses and is then discarded — format selects which rendition is returned, for a companion exactly as for a main document. A filename that is neither this document’s own rendition nor one of its companions is rejected; companion filenames cannot be composed by hand, so copy one verbatim."
    • changedInput schema / properties / format / description
      Previous value: -"markdown (default — the HTML rendition converted to markdown), html (raw HTML rendition), xml (RIS Nutzdaten schema), or urls_only (no fetch — all rendition URLs incl. the authentic PDF)."New value: +"markdown (default — the HTML rendition converted to markdown, and the format for reading), html (raw HTML rendition), xml (RIS Nutzdaten schema), or urls_only (no fetch — all rendition URLs incl. the authentic PDF). html and xml over 40,000 bytes return kind: link with no text — nearly every html rendition does, since each carries a 40–70 KB stylesheet — so fetch content_urls.html or content_urls.xml for the whole artifact."
    • changedInput schema / properties / sections / description
      Previous value: -"Entry names to retrieve, each copied verbatim from a prior outline response (kind: outline) — §/Artikel/Anlage section names, or window names of the form \"Part 2 of 6\". Omit for the full document, which returns an outline instead when the markdown overflows the 40,000-byte budget. A name that matches no entry is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched entries with a notice naming others to pick from. Applies to markdown only — html, xml, and urls_only are never sliced and return in full."New value: +"Entry names to retrieve, each copied verbatim from a prior outline response (kind: outline) — §/Artikel/Anlage section names, or window names of the form \"Part 2 of 6\". Omit for the full document, which returns an outline instead when the markdown overflows the 40,000-byte budget. A name that matches no entry is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched entries with a notice naming others to pick from. Applies to markdown only. html and xml are never sliced — the selector is ignored with a notice, and they return whole under the 40,000-byte budget and as kind: link over it; urls_only carries no text to select from."
    • changedOutput schema / properties / byte_size / description
      Previous value: -"Full UTF-8 byte size of the document text. Present when text was fetched — for an overflowed document (kind: outline) this reports the full text’s size, not the outline payload’s."New value: +"Full UTF-8 byte size of the document text. Present when text was fetched — for an overflowed document (kind: outline) or an over-budget html/xml rendition (kind: link) this reports the full text’s size, not the returned payload’s."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the host + /Dokumente/ path-prefix allowlist, its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the origin + /Dokumente/ path-prefix allowlist (exactly https://www.ris.bka.gv.at and https://ogd.ris.bka.gv.at), its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / kind / description
      Previous value: -"full — the complete response (document text, selected entries, or rendition URLs). outline — sections lists the retrievable entries instead of the text, either because the document overflowed the byte budget or because a sections:[…] selector matched nothing; re-call with sections:[…] naming entries from it."New value: +"full — the complete response (document text, selected entries, or rendition URLs). outline — sections lists the retrievable entries instead of the text, either because the markdown overflowed the byte budget or because a sections:[…] selector matched nothing; re-call with sections:[…] naming entries from it. link — an html or xml rendition over the 40,000-byte budget: no text, only byte_size and content_urls, whose entry for the requested format fetches the whole artifact in one GET; re-call with format: markdown to read it."
    • changedOutput schema / properties / kind / enum
      Previous value: -[
      -  "full",
      -  "outline"
      -]New value: +[
      +  "full",
      +  "outline",
      +  "link"
      +]
    • changedOutput schema / properties / notice / description
      Previous value: -"Present when the requested text format is unavailable for this application (names why and the usable URL), when the document overflowed to a section outline (names how to retrieve sections), or when a sections:[…] entry matched no section (names the unmatched entries)."New value: +"Present when the requested text format is unavailable for this application (names why and the usable URL), when the document overflowed to a section outline (names how to retrieve sections), when an html or xml rendition overflowed to a link (names content_urls.<format> and format: markdown), or when a sections:[…] entry matched no section or was ignored (names the unmatched entries)."
    • changedOutput schema / properties / text / description
      Previous value: -"The document text in the requested format. Absent for urls_only and when the application carries no text rendition (see the notice)."New value: +"The document text in the requested format. Absent for urls_only, when the application carries no text rendition (see the notice), for an outline (kind: outline), and for an html or xml rendition over the 40,000-byte budget (kind: link)."
    • changedOutput schema / properties / truncated / description
      Previous value: -"Present and true when the full text isn’t inline because an outline was returned instead (kind: outline) — either the document overflowed the byte budget, or a sections:[…] selector matched nothing. The notice names which. Retrieve entries via the sections input, or fetch content_urls for the whole artifact."New value: +"Present and true when the full text isn’t inline. kind: outline — the markdown overflowed the byte budget or a sections:[…] selector matched nothing (the notice names which); retrieve entries via the sections input. kind: link — an html or xml rendition overflowed the budget; fetch content_urls.html or content_urls.xml for the whole artifact, or re-call with format: markdown."
  5. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "format",
      +      "kind",
      +      "binding_status",
      +      "content_urls",
      +      "document_number",
      +      "application"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / error
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Present when the call failed. Absent on success.",
      +  "properties": {
      +    "code": {
      +      "description": "JSON-RPC error code for this failure.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "data": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "reason": {
      +          "description": "Machine-readable failure mode. Declared by this tool: `invalid_addressing`: Neither or both addressing modes were provided, document_number was given without application, or the document_number/application pairing is not a valid RIS document — thrown locally before any fetch. `unsupported_url`: document_url fails the host + /Dokumente/ path-prefix allowlist, its path segment is not a recognized RIS application, or its trailing filename addresses neither the document’s own rendition nor one of its companion documents — thrown locally, nothing fetched. `document_not_found`: The constructed or passed content URL returned 404. `upstream_error`: The RIS content host was unreachable or returned a server error. `upstream_timeout`: The content host did not return the rendition within the fetch deadline — typically a cold render, which it performs on first request before caching the result. Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "invalid_addressing",
      +            "unsupported_url",
      +            "document_not_found",
      +            "upstream_error",
      +            "upstream_timeout"
      +          ],
      +          "type": "string"
      +        },
      +        "recovery": {
      +          "additionalProperties": {},
      +          "description": "Actionable next step for the caller.",
      +          "properties": {
      +            "hint": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "hint"
      +          ],
      +          "type": "object"
      +        },
      +        "retryable": {
      +          "description": "Whether retrying may succeed.",
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "message": {
      +      "description": "Human-readable description of what went wrong.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "message"
      +  ],
      +  "type": "object"
      +}
    • removedOutput schema / required
      Removed value: -[
      -  "format",
      -  "kind",
      -  "binding_status",
      -  "content_urls",
      -  "document_number",
      -  "application"
      -]
  6. Changed7 schema fields changed
    • changedInput schema / properties / document_url / description
      Previous value: -"A https://www.ris.bka.gv.at/Dokumente/… rendition URL as returned in a result’s content_urls — the alternative to document_number + application. Also the only way to read a draft’s companion documents: pass a URL from a ris_search_drafts record’s materials[].urls (Materialien_/Schreiben_/Anlagen_… — the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Any other filename is rejected."New value: +"A https://www.ris.bka.gv.at/Dokumente/… rendition URL as returned in a result’s content_urls — the alternative to document_number + application. Also the only way to read a draft’s companion documents: pass a ris_search_drafts record’s materials[].url (the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Every companion filename RIS publishes is accepted, whichever shape it carries. The URL’s own extension is only checked against the rendition extensions RIS uses and is then discarded — format selects which rendition is returned, for a companion exactly as for a main document. A filename that is neither this document’s own rendition nor one of its companions is rejected; companion filenames cannot be composed by hand, so copy one verbatim."
    • changedInput schema / properties / sections / description
      Previous value: -"Section names to retrieve, each copied verbatim from a prior outline response (kind: outline). Omit for the full document — which returns a §/Artikel/Anlage outline instead when the markdown overflows the 40,000-byte budget and carries at least two such headings. A name that matches no section is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched sections with a notice naming other sections to pick from. Applies to markdown only — html, xml, and urls_only carry no headings to select from and return in full."New value: +"Entry names to retrieve, each copied verbatim from a prior outline response (kind: outline) — §/Artikel/Anlage section names, or window names of the form \"Part 2 of 6\". Omit for the full document, which returns an outline instead when the markdown overflows the 40,000-byte budget. A name that matches no entry is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched entries with a notice naming others to pick from. Applies to markdown only — html, xml, and urls_only are never sliced and return in full."
    • changedOutput schema / properties / content_urls / description
      Previous value: -"Constructed rendition URLs. Empty for authentic-PDF-only (Bvb/GrA/KmGer) and metadata-only (BgblAlt) applications — see authentic_pdf_url and the notice. For a companion document (a draft’s Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex) these are the companion’s own XML/HTML/PDF, not the parent document’s."New value: +"Constructed rendition URLs. Empty for authentic-PDF-only (Bvb/GrA/KmGer) and metadata-only (BgblAlt) applications — see authentic_pdf_url and the notice. For a companion document (a draft’s Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex) these are the companion’s own XML/HTML/PDF, not the parent document’s — constructed rather than read back from RIS, so for the roughly one companion in eight that RIS files as a PDF only, xml and html return 404 and pdf is the one that resolves."
    • changedOutput schema / properties / kind / description
      Previous value: -"full — the complete response (document text, selected sections, or rendition URLs). outline — sections lists the retrievable §/Artikel/Anlage units instead of the text, either because it overflowed the byte budget or because a sections:[…] selector matched nothing; re-call with sections:[…] naming entries from it."New value: +"full — the complete response (document text, selected entries, or rendition URLs). outline — sections lists the retrievable entries instead of the text, either because the document overflowed the byte budget or because a sections:[…] selector matched nothing; re-call with sections:[…] naming entries from it."
    • changedOutput schema / properties / sections / description
      Previous value: -"Present when kind = outline: the document’s §/Artikel/Anlage sections, largest first, each with its UTF-8 byte size. Copy names into the sections input verbatim to retrieve them."New value: +"Present when kind = outline: the document’s addressable entries, each with its UTF-8 byte size — §/Artikel/Anlage sections listed largest first, or, when the markdown carries no such headings, Part n of N byte windows listed in document order and summing to byte_size. Copy names into the sections input verbatim to retrieve them; naming several in one call returns their text concatenated in document order, with nothing inserted between them."
    • changedOutput schema / properties / sections / items / description
      Previous value: -"A retrievable §/Artikel/Anlage section — its name and UTF-8 byte size."New value: +"A retrievable entry — a §/Artikel/Anlage section or a Part n of N byte window, with its UTF-8 byte size."
    • changedOutput schema / properties / truncated / description
      Previous value: -"Present and true when the full text isn’t inline because a section outline was returned instead (kind: outline) — either the document overflowed the byte budget, or a sections:[…] selector matched nothing. The notice names which. Retrieve sections via the sections input, or fetch content_urls for the whole artifact."New value: +"Present and true when the full text isn’t inline because an outline was returned instead (kind: outline) — either the document overflowed the byte budget, or a sections:[…] selector matched nothing. The notice names which. Retrieve entries via the sections input, or fetch content_urls for the whole artifact."
  7. Changed3 schema fields changed
    • changedInput schema / properties / document_url / description
      Previous value: -"A https://www.ris.bka.gv.at/Dokumente/… main-document rendition URL as returned in a result’s content_urls — the alternative to document_number + application. Must address a main-document rendition ({documentNumber}.{ext}); content-attachment URLs (Materialien_/Anlagen_… memoranda and annexes) are not fetchable this way."New value: +"A https://www.ris.bka.gv.at/Dokumente/… rendition URL as returned in a result’s content_urls — the alternative to document_number + application. Also the only way to read a draft’s companion documents: pass a URL from a ris_search_drafts record’s materials[].urls (Materialien_/Schreiben_/Anlagen_… — the Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex), whose filenames are opaque and per-record and so cannot be reached through document_number. Any other filename is rejected."
    • changedInput schema / properties / sections / description
      Previous value: -"Section names to retrieve, each copied verbatim from a prior outline response (kind: outline). Omit for the full document — which returns a §/Artikel/Anlage outline instead when the markdown overflows the byte budget. A name that matches no section is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched sections with a notice naming the rest. Applies to markdown only — html, xml, and urls_only carry no headings to select from and return in full."New value: +"Section names to retrieve, each copied verbatim from a prior outline response (kind: outline). Omit for the full document — which returns a §/Artikel/Anlage outline instead when the markdown overflows the 40,000-byte budget and carries at least two such headings. A name that matches no section is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched sections with a notice naming other sections to pick from. Applies to markdown only — html, xml, and urls_only carry no headings to select from and return in full."
    • changedOutput schema / properties / content_urls / description
      Previous value: -"Constructed rendition URLs. Empty for authentic-PDF-only (Bvb/GrA/KmGer) and metadata-only (BgblAlt) applications — see authentic_pdf_url and the notice."New value: +"Constructed rendition URLs. Empty for authentic-PDF-only (Bvb/GrA/KmGer) and metadata-only (BgblAlt) applications — see authentic_pdf_url and the notice. For a companion document (a draft’s Erläuterungen, Textgegenüberstellung, WFA, cover letter, or annex) these are the companion’s own XML/HTML/PDF, not the parent document’s."
  8. Changed5 schema fields changed
    • changedInput schema / properties / sections / description
      Previous value: -"Section names to retrieve, each copied verbatim from a prior outline response (kind: outline). Omit for the full document — which returns a §/Artikel/Anlage outline instead when the markdown overflows the byte budget. Applies to markdown only — ignored for html, xml, and urls_only, which return in full and have no outline to select from."New value: +"Section names to retrieve, each copied verbatim from a prior outline response (kind: outline). Omit for the full document — which returns a §/Artikel/Anlage outline instead when the markdown overflows the byte budget. A name that matches no section is never silently ignored: a total miss returns the outline (kind: outline) with a notice, a partial miss returns the matched sections with a notice naming the rest. Applies to markdown only — html, xml, and urls_only carry no headings to select from and return in full."
    • changedOutput schema / properties / kind / description
      Previous value: -"full — the complete response (document text, selected sections, or rendition URLs). outline — the text overflowed the byte budget, so sections lists the retrievable §/Artikel/Anlage units; re-call with sections:[…] to fetch specific ones."New value: +"full — the complete response (document text, selected sections, or rendition URLs). outline — sections lists the retrievable §/Artikel/Anlage units instead of the text, either because it overflowed the byte budget or because a sections:[…] selector matched nothing; re-call with sections:[…] naming entries from it."
    • changedOutput schema / properties / notice / description
      Previous value: -"Present when the requested text format is unavailable for this application (names why and the usable URL), or when the document overflowed to a section outline (names how to retrieve sections)."New value: +"Present when the requested text format is unavailable for this application (names why and the usable URL), when the document overflowed to a section outline (names how to retrieve sections), or when a sections:[…] entry matched no section (names the unmatched entries)."
    • changedOutput schema / properties / sections / description
      Previous value: -"Present when kind = outline: the document’s §/Artikel/Anlage sections, largest first, each with its UTF-8 byte size. Copy names into the sections input to retrieve them."New value: +"Present when kind = outline: the document’s §/Artikel/Anlage sections, largest first, each with its UTF-8 byte size. Copy names into the sections input verbatim to retrieve them."
    • changedOutput schema / properties / truncated / description
      Previous value: -"Present and true when the full text isn’t inline because the document overflowed to a section outline (kind: outline) — retrieve sections via the sections input, or fetch content_urls for the whole artifact."New value: +"Present and true when the full text isn’t inline because a section outline was returned instead (kind: outline) — either the document overflowed the byte budget, or a sections:[…] selector matched nothing. The notice names which. Retrieve sections via the sections input, or fetch content_urls for the whole artifact."
  9. Changed2 schema fields changed
    • changedInput schema / properties / sections / description
      Previous value: -"Section names to retrieve, each copied verbatim from a prior outline response (kind: outline). Omit for the full document — which returns a §/Artikel/Anlage outline instead when the markdown overflows the byte budget. Applies to text formats; ignored for urls_only."New value: +"Section names to retrieve, each copied verbatim from a prior outline response (kind: outline). Omit for the full document — which returns a §/Artikel/Anlage outline instead when the markdown overflows the byte budget. Applies to markdown only — ignored for html, xml, and urls_only, which return in full and have no outline to select from."
    • changedOutput schema / properties / notice / description
      Previous value: -"Agent-facing notice: either the requested text format is unavailable for this application (names why and the usable URL), or the document overflowed to a section outline (names how to retrieve sections)."New value: +"Present when the requested text format is unavailable for this application (names why and the usable URL), or when the document overflowed to a section outline (names how to retrieve sections)."
  10. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare read-only, open-world, and idempotent behavior. The description adds substantial non-annotation context: binding_status, per-application format availability, explicit degradation to format_unavailable notices, no OCR, a 40,000-byte budget with outline fallback, and stylesheet-induced link responses for html. It does not contradict annotations, and it discloses operational limits well beyond 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.

Conciseness3/5

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

The purpose is front-loaded and the sequence is logical, but the description is a dense wall of text with long parentheticals. Several points, such as the 40–70 KB stylesheet and html returning kind: link, duplicate the input schema descriptions, adding length without new information for an agent that reads both.

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 a complex multi-format tool with an output schema, the description covers addressing modes, format degradation, outline retrieval, and binding status. It explains the important edge cases (PDF-only applications, BgblAlt metadata-only, no OCR, link fallback) and does not need to restate return values because the output schema exists.

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 coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by mapping format availability to application types, explaining when urls_only is the only safe call, and detailing sections behavior with outline and mismatch notices. Some of this repeats the schema's own parameter descriptions, but the per-application format guidance is new.

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 opening sentence states a specific verb and resource: fetching one RIS document's full text or rendition URLs, with binding status and authentic PDF surfaced. It explicitly distinguishes itself from search/lookup siblings by noting it returns content, not fresh metadata, so an agent knows exactly what it is for.

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?

Gives explicit alternatives for addressing a document (document_number+application vs. document_url), names ris_search_* and ris_lookup_citation as sources for those values, and reserves ris_search_drafts materials[].url as the only route to companion documents. It also states format choices and their trade-offs, plus when to use sections after an outline, leaving little to inference.

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.