Sök svenska aktiebolag och hämta bokslut, nyckeltal och registeruppgifter.
Scored across 3 tools
Each tool has a clearly distinct purpose: sok_foretag searches for an organization number, hamta_foretag retrieves register details and latest key figures, and hamta_bokslut returns full financial statements. The descriptions explicitly call out that the other tools require an organization number, reinforcing the search-then-retrieve workflow.
All tool names follow a consistent verb_noun pattern in Swedish with snake_case: sok_foretag, hamta_foretag, hamta_bokslut. The verbs (sok/hamta) appropriately distinguish search from retrieval, and the objects are clear and consistent.
Three tools is a well-scoped set for a focused Swedish company data server. Each tool earns its place: search, company details, and detailed financial statements, with no redundant or filler tools.
The core workflow is covered: find a company, get its register data and key figures, and retrieve full financial statements for any available year. Minor gaps exist such as no advanced filtering or corporate structure exploration, but these are outside the apparent narrow scope.
Fullständig resultat- och balansräkning ur bolagets egen årsredovisning. Utan år ges alla år som sammandrag; med år ges hela uppställningen post för post. Belopp i kronor, precis som bolaget lämnat dem – ingenting räknas om. Knappt två tredjedelar av aktiebolagen lämnar årsredovisning digitalt och har därför bokslut här; för övriga är listan tom. De börsnoterade moderbolagen saknas, deras svenska dotterbolag inte.
| Name | Required | Description | Default |
|---|---|---|---|
| ar | No | Räkenskapsårets slutår, t.ex. 2024. | |
| orgnr | Yes | Organisationsnummer, med eller utan bindestreck. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden, and it does this well: it discloses amounts are in kronor as originally filed, that data availability depends on digital filing, and that listed parent companies are missing. It stops short of explicitly stating response format or error behavior, but the read-only nature is clear from 'Hämta'.
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 dense but well-organized, with the core function first, then parameter behavior, then data-coverage caveats. Every sentence adds useful information; there is no filler or repetition.
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?
For a simple two-parameter, one-required tool with no output schema, the description covers the critical context: parameter behavior, currency, data coverage, and known gaps. It does not detail the exact response schema or empty-result handling, but nothing essential to choosing and invoking the tool correctly is missing.
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?
Schema coverage is 100%, so baseline is 3. The description adds meaningful extra semantics for the 'ar' parameter by explaining the different output shapes when it is omitted versus provided, going beyond the schema's bare description of 'Räkenskapsårets slutår'.
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?
Description states a specific resource: 'Fullständig resultat- och balansräkning ur bolagets egen årsredovisning' – a clear verb-plus-resource definition. It distinguishes itself from siblings (hamta_foretag, sok_foretag) by focusing on bokslut rather than company records.
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 gives clear parameter-dependent usage: without 'ar' all years are returned as a summary; with 'ar' the full statement is returned item by item. However, it never explicitly says when to choose this tool over sibling tools like hamta_foretag or sok_foretag; the routing is only implied by the tool name and subject matter.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Registeruppgifter och senaste nyckeltal för ett företag: namn, status, organisationsform, adress, bransch, registreringsdatum, omsättning, resultat, anställda och soliditet. Belopp i kronor. Ett fält som är null betyder att uppgiften inte redovisats – inte att den är noll.
| Name | Required | Description | Default |
|---|---|---|---|
| orgnr | Yes | Organisationsnummer, med eller utan bindestreck. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description adds useful interpretation semantics: 'Belopp i kronor' and, importantly, that null means 'uppgift saknas' rather than zero. This prevents misreading missing data. It does not mention error/not-found behavior or data freshness, so it falls short of a 5.
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 compact and front-loaded: it states the resource and content in the first sentence, then appends two short, high-value clarifications (currency and null semantics). No redundant wording.
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?
For a simple lookup tool with one parametercars and a light output schema, the description covers the needed selection and interpretation information well. It lacks only an explicit pointer to siblings (e.g., 'use sok_foretag to search without a known org number').
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?
Schema coverage is high: the single orgNr parameter is described in the schema as 'med eller utan bindestreck'. The description adds no parameter-specific details beyond that, so the baseline of 3 is appropriate.
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 identifies the operation ('Retrieve company registration data and latest key figures') and enumerates the returned fields. It does not explicitly contrast with sibling tools such as hamta_bokslut or sok_foretag, which prevents a 5.
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?
No explicit guidance is given on when to use this tool versus the siblings hamta_bokslut or sok_foretag. The intended use (fetching a company by org number) is only implied by the description and the required parameter.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sök svenska företag på namn eller organisationsnummer. Ger de främsta träffarna med organisationsnummer, ort, status och senaste omsättning. Använd det här först när du bara har ett namn – de andra verktygen kräver organisationsnummer. Täcker alla registrerade svenska bolag, även avregistrerade.
| Name | Required | Description | Default |
|---|---|---|---|
| fraga | Yes | Företagsnamn eller organisationsnummer. | |
| limit | No | Antal träffar, 1–50. Förval 10. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns top matches, includes key fields, and covers all registered Swedish companies including deregistered ones. While it does not discuss ranking or no-result behavior, the disclosed scope and output traits are meaningful and non-obvious.
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?
Three compact sentences, each earning its place: what the tool searches, what it returns, when to use it, and what data coverage it has. The most decision-relevant usage guidance is front-loaded immediately after the core purpose.
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?
For a simple search tool with two fully documented parameters and no output schema, the description provides sufficient context: input types, key output fields, coverage, and explicit routing against siblings. Nothing an agent needs to invoke it correctly is missing.
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?
Schema description coverage is 100%, and the schema already documents 'fraga' as company name or organizationsnummer and 'limit' as hit count with default. The description reinforces that fraga accepts either input type, but adds no new parameter semantics beyond the schema, so the baseline of 3 applies.
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 opens with a specific verb and resource: 'Sök svenska företag på namn eller organisationsnummer.' It clearly states what results are returned and differentiates from siblings by noting that other tools require an organizationsnummer, making the tool's role unambiguous.
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 gives explicit usage guidance: 'Använd det här först när du bara har ett namn – de andra verktygen kräver organisationsnummer.' This tells an agent exactly when to choose this tool over alternatives and why, which is strong contextual routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
hamta_boksluthamta_foretagsok_foretagDanish company registry (CVR): company search, financials, ownership, beneficial owners and more.
Vyhledávání a detail českých firem, finanční výkazy a ukazatele z veřejných rejstříků.
EU company registry lookup across 16 countries incl. Sweden Bolagsverket.
Swedish B2B intelligence: insolvency risk, BRF health & procurement signals from govt registries.
Add one secure layer between your agents and this server.
