sweden-parliament-mcp-server

Read parliamentary document

riksdag_get_document

Read-onlyIdempotent

Read a document status, decisions, linked records and text. Select sections and follow complete continuation calls to read long reports or consolidated SFS statutes. SFS text is consolidated published text, not a point-in-time legal version.

Input Schema

Name	Required	Description
`revision`	No	Revision returned by a previous call; rejects changed records.
`sections`	No	Select metadata, decisions, reservations, activities, properties, attachments, references, stakeholders, text or source_html. Omit for metadata, complete outline and first text page.
`documentId`	Yes	Document ID from riksdag_search_documents, or unambiguous SFS YYYY:N identifier.
`htmlLength`	No	Explicit source HTML length in code points; defaults start at 8000 and fit the complete response; explicit lengths are honored.
`htmlOffset`	No	Source HTML offset in Unicode code points.
`textLength`	No	Explicit text length in code points; defaults start at 8000 and fit the complete response; explicit lengths are honored.
`textOffset`	No	Text offset in Unicode code points.
`sectionLimit`	No	Requested entries per selected array section; applied maximum 100.
`sectionOffset`	No	Offset applied independently to each selected array section.

Output Schema

Name	Required	Description
`text`	No	Selected canonical text page, unchanged on both surfaces.
`error`	No	Present when the call failed. Absent on success.
`found`	No	Whether the source record exists.
`source`	No	Required attribution to the Swedish Parliament.
`notices`	No	All applicable notices, including an empty list.
`outline`	No	Every selectable section and its complete size.
`guidance`	No	How to resolve a missing identifier.
`metadata`	No	Source publication metadata and links.
`revision`	No	Hash of the complete normalized record.
`decisions`	No	Selected page of authoritative report points.
`truncated`	No	At least one selected array section has more entries or a response-fitted page; follow its sectionPages continuation.
`activities`	No	Selected process-event page.
`documentId`	No	Normalized document identifier.
`htmlOffset`	No	Returned HTML offset in code points.
`properties`	No	Selected property page.
`references`	No	Selected relationship page.
`sourceHtml`	No	Separately selected original source HTML page.
`textOffset`	No	Returned text offset in Unicode code points.
`attachments`	No	Selected linked-attachment page.
`htmlHasMore`	No	Whether source HTML remains.
`retrievedAt`	No	Source fetch time, retained unchanged on cache hits.
`textHasMore`	No	Whether canonical text remains.
`nextHtmlCall`	No	Complete continuation for source HTML.
`nextTextCall`	No	Complete continuation for canonical text.
`reservations`	No	Selected reservation page.
`sectionPages`	No	Independent counts and complete continuation for every selected array.
`stakeholders`	No	Selected page of source participants, retaining entries without an IID.
`textAvailable`	No	Whether a published canonical body exists.
`upstreamQuery`	No	Upstream query echo; not proof that a filter was applied.
`effectiveQuery`	No	Deterministic normalized input, applied defaults and local filters.
`htmlTotalLength`	No	Complete HTML code-point length.
`textTotalLength`	No	Complete canonical text length in code points.
`upstreamWarnings`	No	Warnings supplied by the source.
`htmlReturnedLength`	No	Returned HTML code points.
`textRepresentation`	No	Source SFS text or canonical converted Markdown.
`textReturnedLength`	No	Actual returned text code points.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld, so the extra burden is modest; the description still adds real value by disclosing pagination/continuation behavior and the consolidated-vs-historical SFS caveat, which an agent could otherwise get wrong.

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?

Three sentences, front-loaded with what is returned, then the paging mechanism, then the SFS caveat. Dense but every sentence carries information; no filler.

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 an output schema and full parameter documentation, the description only needs to cover the paging model and the SFS interpretation caveat, both of which it does. Revision-conflict semantics are left entirely to the schema, a minor gap.

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 baseline is 3, but the description adds operational meaning the schema does not: that sections can be selected and that continuation calls are the mechanism for long documents. It still leaves the offset/length and sectionLimit interplay to 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?

Specific verb ('Read') plus resource ('document') and an enumeration of what is returned (status, decisions, linked records, text). It implicitly contrasts with riksdag_search_documents by dealing with a single identified document, and the SFS note flags a distinct content type, but it does not explicitly name a sibling.

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?

Explains when to select sections, when to follow continuation calls for long reports, and warns that SFS text is consolidated rather than point-in-time. Missing an explicit 'use riksdag_search_documents first to obtain a documentId' routing statement, though the schema supplies it.

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

All sweden-parliament-mcp-server 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.