Företagskoll – Swedish company data

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely useful context beyond them: the upstream sources (Bolagsverket, SCB) and, importantly, the pricing model — $0.01 USDC on Base via x402, with no charge when the company is not found. That billing behavior is not derivable from any structured field. It does not mention auth requirements or rate limits, keeping it 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?

Front-loaded with the action, then the return fields, then source and cost — each clause carries information an agent needs (especially the field list, which substitutes for the absent output schema). No filler sentences.

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?

With no output schema, describing the returned fields is essential and is done thoroughly, and the cost/source disclosure closes the main behavioral gap. What remains missing is sibling routing (financials vs. validation) and any failure-mode detail beyond the no-charge note.

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% — the org_number property already documents the 10-digit format with dash optional and an example. The description adds no format, validation, or edge-case detail beyond that, so baseline 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?

States a specific verb and resource ('Look up a Swedish company by organisation number') and then enumerates the exact data returned (name, legal form, status, liquidation/bankruptcy, registration date, address, SNI codes, business description). That field list distinguishes it from get_swedish_company_financials without opening either schema.

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 required input (organisation number) implies when the tool is applicable, but there is no explicit guidance on when to prefer it over get_swedish_company_financials or whether validate_swedish_org_number should be called first. Usage is inferable rather than stated.

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

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

Annotations only cover read-only and open-world; the description adds substantial non-obvious behavior: a $0.05 USDC-on-Base x402 charge, the fact that it is not charged when no digital annual report exists, and the Bolagsverket source. It does not describe latency or what the response looks like, but the billing semantics are genuinely valuable context.

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?

Front-loads what the tool returns, then appends source and cost in short clauses. Slightly dense single sentence but every clause (field list, source, price, waiver condition) earns its place.

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?

With no output schema, the description usefully enumerates the returned figures (current and previous year plus growth and margins) and discloses the coverage limit implied by 'latest digitally filed annual report'. Together with the billing note this is close to complete for a one-parameter lookup 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?

Schema description coverage is 100% and there is a single required org_number parameter already documented in the schema with format and example. The description adds no additional meaning beyond the schema, so baseline 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?

States a specific verb+resource: financial figures from a Swedish limited company's latest digitally filed annual report, with an explicit field list. It distinguishes itself from the registry-style sibling get_swedish_company by content scope, though it never names that sibling directly.

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?

Usage is implied by the field list (use when you need revenue, profit, equity, etc.), and the cost/waiver note gives a practical condition. But there is no explicit when-to-use-vs-alternative guidance relative to get_swedish_company or validate_swedish_org_number.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine context beyond that — it discloses that validation covers both format and check digit, that a legal-form hint is returned, and that the call is free — but it never says what happens on invalid input (error vs. boolean result).

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?

A single tight sentence with zero waste; the core action and its scope are front-loaded, with the cost note trailing.

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 single-parameter validation tool with no output schema and safety annotations in place, the definition is nearly sufficient. The one gap is the unstated return shape (valid/invalid flag, parsed legal form), which matters slightly since there is no output schema to fall back on.

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 the 10-digit format, optional dash, and an example. The description adds no parameter-level detail beyond that, so the baseline 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?

States a specific verb (checks) and resource (Swedish organisation number) plus the exact aspects validated: format, check digit, and legal-form hint. This clearly separates it from the get_swedish_company siblings, which retrieve rather than validate, though it never names them explicitly.

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?

Usage is only implied: 'Free' signals a cheap pre-check before calling the paid company-lookup siblings, and the word 'validate' implies a precondition check. There is no explicit when-to-use/when-not statement or named alternative.

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