Server Quality Checklist

Tool Scores

• search_subunitsA
  3.9/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It explains the entity concept ('A subunit shares the parent's organization but has its own orgnr for reporting purposes') and scopes the search to the registry, but does not disclose pagination, return format, authentication, or any side effects. This is adequate for a read-only search tool but not rich.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

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

  The description is three sentences, each purposeful: the first defines the action, the second gives example use cases, and the third clarifies a domain-specific relationship. No redundant filler, front-loaded with the primary purpose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a search tool with 6 optional parameters, no output schema, and no annotations, the description provides a solid purpose and use cases but lacks details on result shape, pagination, and any prerequisites. It is sufficient for basic invocation but incomplete for a fully informed agent.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 67% (4 of 6 parameters described). The description indirectly references filtering by municipality and parent company, aligning with 'kommunenummer' and 'overordnetEnhet', but does not add syntax or format details for these or the pagination parameters. The added domain context slightly improves understanding beyond the schema.

  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 description uses a specific verb ('Searches') and identifies the resource ('subunits (underenheter — branch offices, departments, production sites)') in the Norwegian business registry. It clearly distinguishes from sibling tools like search_companies by focusing on subunits and their parent relationship.

  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?

  The description gives clear typical usage contexts: 'find all branches of a parent company' or 'locate subunits in a specific municipality'. It does not explicitly mention when not to use the tool or name alternative tools, but the use cases strongly imply differentiation from general company search.

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

• get_company_rolesA
  4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral burden. It discloses a key exclusion (no personal identification numbers, which require Maskinporten auth) and describes the return format ('structured role groups with person or entity role-holders'). This goes beyond a simple retrieval statement, though it doesn't cover error handling or pagination.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

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

  The description is two sentences, front-loaded with the action and scope, and uses examples efficiently. No unnecessary jargon or repetition; every sentence contributes useful information.

  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?

  Given the tool's simplicity (one parameter, no output schema, no annotations), the description covers the main functional purpose, a significant exclusion, and the nature of the return value. It could mention error conditions or broader authentication requirements, but it is largely complete for a straightforward retrieval tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema fully documents the only parameter (orgnr as a 9-digit Norwegian organization number) with 100% coverage. The description adds minimal extra meaning beyond noting the Norwegian context, which is already implied by the schema. Baseline for high schema coverage is 3.

  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 description uses a specific verb ('Retrieves') and identifies the exact resource ('all registered roles... for a Norwegian company'). It lists example roles, which clearly distinguishes it from sibling tools like lookup_company or search_companies that focus on other aspects of company data.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage when a company's roles are needed and clarifies that personal identification numbers require separate auth, but it does not explicitly contrast with sibling tools or state when to prefer this tool over alternatives. There is no explicit 'when-to-use' or 'when-not-to-use' guidance.

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

• get_recent_updatesA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It communicates that the tool returns a feed and describes each update's content (orgnr, change type, timestamp), but it does not disclose ordering, pagination behavior, or any potential limitations. This is adequate but not rich.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

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

  The description is two sentences, front-loaded with the main action and resource, and each sentence provides meaningful context (use cases and output shape). No wasted words.

  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?

  For a simple feed tool with three optional parameters and no output schema, the description covers the purpose, use cases, and the core return elements. It could mention pagination or result ordering, but the essentials are present and proportionate to the tool's complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 67% with descriptions for 'dato' and 'oppdateringsid', and 'size' is self-explanatory. The description adds no parameter-specific detail beyond what the schema provides, so it neither strongly compensates nor falls short.

  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 description clearly states the action ('Fetches a feed') and the resource ('entities (companies) that were recently updated in the Norwegian business registry'). It also distinguishes itself from sibling tools like lookup_company and search_companies by emphasizing the update-feed nature and the inclusion of change type and timestamp.

  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?

  The description provides explicit use cases: 'monitoring changes to specific companies' and 'watching for new registrations / status changes.' It does not explicitly mention alternatives or when not to use, but the context is clear enough for an agent to select this tool for update feeds versus lookup/search tools.

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

• search_companiesA
  4/5.0
  Behavior3/5

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

  There are no annotations, so the description carries the full burden. It discloses that results are paginated and that filters include municipality, industry code, organization form, and registration status. However, it does not explicitly state that the operation is read-only, nor does it mention error cases, result ordering, or rate limits. This is adequate but minimal.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

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

  The description consists of two sentences that are compact and front-loaded. The first sentence states the core function, and the second provides usage guidance. There is no wasted wording.

  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?

  For a tool with 9 parameters and no output schema, the description gives sufficient context for selection and invocation. It covers what the tool does and when to use it, but it does not elaborate on the return structure beyond 'paginated list'. The rich schema compensates for most gaps.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline is 3. The description summarizes the filters at a high level but does not add syntax or format details beyond the schema. It meets the minimum viable bar.

  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 description clearly states the tool's function with a specific verb ('Searches'), a resource ('Norwegian business registry'), and scope ('by name and optional filters'). It distinguishes itself from siblings by emphasizing search over lookup and mentioning paginated results.

  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?

  The description explicitly provides usage context with 'Use this when the user wants to find a company by name, or filter by...' It does not explicitly name alternative tools or exclusions, but the guidance is clear enough for an agent to select this tool for search scenarios.

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

• lookup_companyA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries full burden. It discloses the operation as a read ('Retrieves') and lists specific return fields (name, address, NACE codes, etc.), which is useful context. It does not mention error handling for invalid org numbers, but the scope is clear.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

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

  Two sentences: the first clearly states the function and output, the second provides usage guidance. No redundant wording, well-structured and front-loaded.

  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 a single parameter and no output schema, the description provides a comprehensive list of return fields, the data source, and when to use it. It lacks explicit handling of invalid or missing org numbers or rate limits, but these are minor for a simple lookup tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, with the schema already describing 'orgnr' as a 9-digit Norwegian organization number with an example. The description adds no new parameter information beyond repeating the 9-digit format. Baseline 3 is appropriate.

  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 description clearly states the tool retrieves full details of a Norwegian business entity by its 9-digit organization number. The verb 'Retrieves' and specific resource (Brønnøysund Register Centre) distinguish it from sibling tools like search_companies (search) and get_company_roles (roles).

  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?

  Explicitly says 'Use this when the user provides or asks about a specific Norwegian orgnr.' This gives clear context for when to invoke the tool. It doesn't explicitly mention alternatives, but the sibling tool names imply search for vague queries, and the condition is precise.

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