Server Quality Checklist

Tool Scores

• get_prespec_opinionsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds valuable context: data is limited to Jan 2025 onward, and parallel query behavior when kind unspecified. No contradictions, so score 4.

  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?

  Three well-structured sentences, front-loaded with the core purpose. Every sentence adds value, no fluff. Excellent conciseness.

  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 complexity (6 parameters, no output schema), the description is reasonably complete. It covers data recency, parallel behavior, and dependency on sibling tools. Could mention pagination defaults, but strong overall.

  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 schema already documents all 6 parameters. The description adds minor value by stating specRegistNo takes priority over dates, but adds no new meaning beyond what the schema provides. 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's purpose: listing opinions/answers on a specific pre-specification (by registNo). It uses specific verb-resource combination and explicitly distinguishes from sibling search_prespecs tools, scoring a 5.

  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 clear guidance: use after obtaining registNo from search_prespecs, and explains behavior when kind is unspecified (parallel query). It lacks explicit when-not guidance but the sibling reference serves as a clear alternative, earning a 4.

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

• search_prespecs_by_institutionA
  4.4/5.0
  Behavior4/5

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

  Annotations already indicate readOnly and openWorld hints. The description adds valuable behavioral context: the parallel search across all classifications when kind is omitted, and data recency (post-January 2025). This goes beyond the annotated metadata without contradicting it.

  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 concise (4 sentences) and front-loaded with the core purpose. Every sentence earns its place: purpose, use case, sibling differentiation, special behavior, and data scope.

  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 7-parameter read-only search tool with no output schema, the description covers purpose, usage scenarios, special behavior, and data recency. Missing explicit clarification on whether orderInstitution and demandInstitution combine as AND or OR, but overall adequate.

  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 baseline is 3. The description repeats the kind behavior already in the schema and contextualizes the institution parameters, but adds minimal new parameter-level detail beyond what the schema descriptions provide.

  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 searches by ordering institution or demand institution, and identifies specific use case (viewing expected order quantities). It also differentiates from sibling tools by naming search_prespecs_by_product and search_prespecs_advanced.

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

  Usage Guidelines5/5

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

  The description explicitly advises using alternative tools for product-based or multi-condition searches, and notes the behavior when business classification is unspecified. This provides clear guidance on when to use this tool versus alternatives.

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

• search_prespecs_by_productA
  4.6/5.0
  Behavior5/5

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

  Beyond annotations (readOnlyHint, openWorldHint), the description reveals that when 'kind' is unspecified, the tool performs parallel queries across all divisions, and that data is limited to registrations after January 2025. No contradictions with annotations.

  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?

  Description is concise with four sentences. The first sentence states the main purpose, followed by usage guidance and behavioral notes. No redundant 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?

  For a tool with 8 parameters (all documented in schema), the description covers purpose, usage, uniqueness, data scope, and behavioral note. Minor missing: defaults for pagination and date range, but those are in schema. Adequate overall.

  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 baseline is 3. The description briefly mentions key parameters (품명, 세부품명) but does not add significant additional meaning beyond the schema descriptions.

  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 '조회' (search) and resource '사전규격' (pre-specifications), specifying the search criteria as 품명 and 세부품명. It explicitly distinguishes from sibling tools by naming alternatives and their use cases.

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

  Usage Guidelines5/5

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

  Provides explicit when-to-use context ('관심 품목의 사전규격을 찾을 때'), names alternative tools for other cases, and notes that detail product name search is unique to this tool. Also explains behavior when no 업무구분 is specified and data recency.

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

• search_prespecs_advancedA
  4.7/5.0
  Behavior5/5

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

  Annotations provide readOnlyHint and openWorldHint. Description adds significant behavioral context: priority order (specRegistNo > refNo > receipt date), data range (post-January 2025), and parallel search when kind is unspecified. No contradictions.

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

  Conciseness4/5

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

  Description is concise with a single sentence, but it packs multiple pieces of information. It is front-loaded with the main purpose and flows logically. Could be slightly restructured for readability, but overall efficient.

  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 complexity (12 parameters, multiple filters), the description covers purpose, usage guidelines, behavioral traits, and parameter context. Missing explicit mention of output format, but for a search tool with no output schema, this is acceptable. Data range and prioritization are well covered.

  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 covers all 12 parameters with descriptions (100% coverage), so baseline is 3. The description adds overall parameter context like priority rules and data range, which aids in selecting parameters but does not elaborate on each parameter individually. This extra context justifies a 4.

  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 searches for prespecs with complex conditions using multiple filters (institution, product name, reference number, SW business status). It distinguishes from siblings by explicitly noting that product name search is not supported and directs to search_prespecs_by_product.

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

  Usage Guidelines5/5

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

  Explicitly explains when to use this tool (multiple filters), when not to (product name search), and provides alternative sibling. Also covers priority order and behavior when kind is unspecified.

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

• search_prespecsA
  4.8/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint and openWorldHint. Description adds that when kind is not specified, all categories are searched in parallel, and data is limited to after January 2025. No contradiction.

  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?

  Description is concise with only essential sentences, front-loaded with purpose and usage guidance. No redundancy.

  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 7 parameters and no output schema, description covers purpose, usage, behavioral details, and parameter defaults well. Lacks explicit output format but acceptable for a search tool with high schema coverage and annotations.

  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%, so baseline is 3. Description adds value by explaining default behavior for kind (parallel search when unspecified) and the data date limitation, which are not in schema descriptions.

  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 tool searches prespecs by date range or registration number, using specific verbs and resources. It also distinguishes from sibling tools by naming alternatives.

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

  Usage Guidelines5/5

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

  Explicitly tells when to use this tool (simple date/number search) and when to use alternatives (by institution, by product, advanced search). Provides clear decision guidance.

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