Sök i Regeringskansliets dokument via g0v.se
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Dokumenttyp (t.ex. pressmeddelanden, propositioner, sou, ds, dir, remisser, regeringsuppdrag, rapporter, tal, debattartiklar, uttalanden, artiklar) | |
| limit | No | Max antal resultat (default: 10 för att minska response-storlek) | |
| title | No | Titel att söka efter | |
| dateTo | No | Till datum (YYYY-MM-DD) | |
| dateFrom | No | Från datum (YYYY-MM-DD) | |
| departement | No | Departement |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility for behavioral disclosure. It only states that the tool searches documents, but does not describe the output format, pagination, rate limits, or whether the search covers full text or metadata. This is a significant transparency gap for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, succinct sentence in Swedish, which is appropriately brief. It avoids unnecessary verbosity, though it sacrifices useful detail for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the schema covering parameters, the description lacks essential context such as the tool's unique scope, expected output, or relationship to other search tools. With no annotations and no output schema, this leaves the agent under-informed about how to integrate the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides thorough descriptions for all six parameters, including values and defaults (e.g., limit), so the baseline is 3. The description itself adds no additional parameter context, so it neither enhances nor detracts from the schema's clarity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (search) and resource (Government Offices' documents), and specifies the source via g0v.se. However, it does not differentiate this tool from sibling search tools like search_dokument or enhanced_government_search, which likely perform similar functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no guidance on when to use this tool versus the many sibling search tools. No mention of appropriate use cases, alternatives, or exclusions is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools target specific data types (documents, speeches, votes, members), but there is notable overlap between similar fetch/search tools, such as get_dokument vs get_dokument_innehall, and search_dokument vs search_dokument_fulltext. Descriptions help, but an agent could easily select the wrong tool for a task.
Tool names mix Swedish and English inconsistently (e.g., get_betankanden vs get_dokument, get_regering_document vs get_g0v_document_content). Prefixes vary (get, search, fetch, list, batch, enhanced, analyze, summarize) without a clear pattern, making the set feel haphazard.
With 32 tools, the server is heavy and likely overwhelms an agent. While the domain is broad, many tools could be consolidated (e.g., paginated fetch variants, multiple search methods), and the count exceeds the typical well-scoped range.
The server covers a wide range of Swedish government data: documents, members, votes, questions, reports, and calendars. Minor gaps exist, such as no direct single-vote retrieval or per-member document listing, but the core informational needs are well covered.