Server Quality Checklist

Tool Scores

• sok_barnehageA
  3.7/5.0
  Behavior2/5

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

  No annotations provided; description only mentions returns compact list but lacks disclosure of response format, limits, side effects (read-only), or authentication. Minimal behavioral context.

  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, zero waste, front-loaded with purpose and sibling differentiation.

  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?

  Adequate for a compact search tool but missing details on returned fields, pagination, error behavior, and limits. Would benefit from additional context.

  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% so description adds no extra meaning beyond summarizing filters. Baseline score applied; description adds value for source and compact list but not for params.

  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?

  Description clearly states the verb 'Søk', the resource 'barnehager', the context via 'Nasjonalt barnehageregister', and distinguishes from sibling 'hent_barnehage' which provides details with coordinates.

  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?

  Description implies usage for compact listing and directs to 'hent_barnehage' for details, but does not explicitly state when not to use or provide exclusions.

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

• hent_barnehageA
  3.8/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It only lists output fields and does not mention whether the operation is read-only, required permissions, rate limits, error conditions, or any side effects. The name implies a read operation, but the description lacks formal disclosure.

  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 a single, front-loaded sentence that efficiently communicates the tool's purpose and output fields with 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 one-parameter tool with no output schema, the description adequately lists the returned fields. It could be improved by mentioning error handling or response format, but given the simplicity, it is largely complete.

  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 tool description does not add additional information about the 'orgnr' parameter beyond what the schema already provides. It merely repeats the source hint, which is already in 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 clearly states the verb 'hent' (get), the resource 'full detalj om én barnehage' (full details about one kindergarten), and lists specific data fields (address, coordinates, ownership, categories, contact info). It distinguishes from sibling tools like 'hent_skole' and 'sok_barnehage' by specifying it retrieves detailed information for a single kindergarten.

  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 implies usage after obtaining an organization number from 'sok_barnehage' (search), but does not explicitly state when to use this tool versus alternatives like 'hent_skole'. The context is clear enough for a simple tool, but lacks an explicit when-not-to-use guide.

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

• sok_skoleA
  4.2/5.0
  Behavior3/5

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

  No annotations provided. Description implies read-only behavior (search, return list) but does not explicitly state destructive safety or auth requirements. It mentions the return is a compact list, which is helpful, but lacks deeper behavioral context like pagination or rate limits.

  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 only, maximum information density, front-loaded with primary action. No unnecessary 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?

  Given no output schema, the description adequately describes the return (compact list) and directs to sibling for details. It covers filtering and defaults. Missing mention of pagination or result limits, but acceptable for a search tool.

  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%, but the description adds valuable details not in the schema: case-insensitive navn filter, normalization of kommunenummer (leading zero, handling '301'), and default for type (alle aktive skoler). This aids correct parameter usage.

  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 'Søk etter skoler i en kommune' with specific verb and resource, and distinguishes from sibling tools by noting that 'hent_skole' provides details. It also differentiates from the barnehage siblings by tool name and context.

  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?

  Provides clear context: filters by name and type, returns compact list, and explicitly recommends 'hent_skole' for detailed info. No explicit when-not guidance, but the alternative is clearly stated.

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

• hent_skoleA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description must convey behavior. It effectively lists the returned data fields, indicating it is a read operation. However, it omits any mention of authorization or rate limits, which would improve transparency.

  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?

  A single sentence efficiently front-loads the purpose and key outputs, with no wasted words. Every element earns its place.

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

  Completeness5/5

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

  For a simple single-parameter read tool, the description covers purpose, input source, and output fields comprehensively. No output schema exists, but the listed fields suffice. No gaps in essential information.

  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 input schema has 100% description coverage for its single parameter 'orgnr', already explaining it is a 9-digit organization number from 'sok_skole'. The description adds no further parameter-level detail beyond what the schema provides.

  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 about one school from NSR (UDIR), listing specific data fields like address, coordinates, enrollment, staff, etc. It distinguishes from sibling tools: 'sok_skole' is for search, 'hent_barnehage' is for kindergartens.

  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 implies usage after obtaining an orgnr from 'sok_skole', providing clear context. It does not explicitly mention when not to use or alternatives, but the context from sibling names is sufficient.

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