Server Quality Checklist

Tool Scores

• get_building_basis_ouln_infoA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It reveals this is a read operation ('조회합니다' - retrieves/reads) and describes pagination behavior through page_no and num_of_rows parameters. However, it doesn't mention authentication requirements, rate limits, error conditions, or whether all parameters are optional (though schema shows all have defaults). The return format is documented, which is helpful.

  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?

  The description is well-structured with clear sections: purpose statement, information scope, parameters with examples, and return format. Each sentence adds value. The parameter documentation is comprehensive but necessary given the poor schema coverage. Slightly verbose but justified by the complexity of 8 parameters needing explanation.

  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 (8 parameters with 0% schema coverage) and no annotations, the description does an excellent job explaining parameter semantics and return format. The output schema exists (implied by the Returns section), so the description appropriately focuses on parameter meaning rather than return value details. The main gap is lack of usage guidance relative to sibling tools, but otherwise provides substantial context for proper tool invocation.

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

  Parameters5/5

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

  With 0% schema description coverage (titles like 'Sigungu Cd' provide no semantic meaning), the description fully compensates by explaining all 8 parameters with Korean translations, format examples, and default values. It provides crucial context that the schema lacks: sigungu_cd is a 5-digit code with examples, bjdong_cd is a 5-digit legal district code, plat_gb_cd indicates land type (0: land, 1: mountain, 2: block), bun/ji are 4-digit parcel numbers, mgm_bldrgst_pk is a management building register PK, and pagination parameters have defaults.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: '건축물대장 기본개요를 조회합니다' (retrieves building register basic overview). It specifies the resource (building register) and the type of information retrieved (basic overview including register type, classification, addresses, zones). However, it doesn't explicitly differentiate from sibling tools like 'get_building_title_info' or 'get_building_floor_ouln_info' which might retrieve different aspects of building information.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. With multiple sibling tools that retrieve different building information aspects (title info, floor info, etc.), there's no indication of when this 'basic overview' tool is appropriate versus more specific tools. No prerequisites, exclusions, or alternative recommendations are mentioned.

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

• get_building_house_price_infoA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals this is a read operation (조회합니다 - retrieve/query) and describes pagination behavior through page_no and num_of_rows parameters. However, it doesn't mention authentication requirements, rate limits, error conditions, or whether all parameters are required. The return format is documented, which is helpful but doesn't cover all behavioral aspects.

  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?

  The description is well-structured with clear sections: purpose statement, elaboration, parameter documentation, and return format. Each sentence earns its place by adding value. The parameter documentation is comprehensive but necessary given the poor schema coverage. The Korean text is concise and to the point without unnecessary elaboration.

  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 (8 parameters, no annotations, 0% schema coverage), the description does a good job of explaining what the tool does, what parameters mean, and what it returns. The output schema exists, so the description appropriately documents the return structure. The main gap is lack of usage guidance relative to sibling tools, but otherwise this is reasonably complete for a data retrieval tool.

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

  Parameters5/5

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

  With 0% schema description coverage (all parameters have generic titles like 'Sigungu Cd'), the description provides essential semantic information for all 8 parameters. It explains what each code represents (시군구코드 = city/county/district code, 법정동코드 = legal district code), provides formatting examples (5자리 = 5 digits, 4자리 = 4 digits), and explains plat_gb_cd values (0: 대지, 1: 산, 2: 블록). This significantly compensates for the lack of schema documentation.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: '건축물대장 주택가격을 조회합니다' (retrieve building register house price information) and specifies it provides '공시가격 정보' (publicly announced price information). It distinguishes itself from siblings by focusing specifically on house prices rather than other building attributes like floor outlines or usage areas. However, it doesn't explicitly contrast with all sibling tools, just implies a specific data domain.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. With multiple sibling tools that retrieve different types of building information (floor outlines, usage areas, titles, etc.), there's no indication of which tool to choose for what specific need. The description assumes the user already knows they need house price information specifically.

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

• get_building_wclf_infoA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly indicates this is a read operation ('조회합니다' - retrieves/reads) and describes pagination behavior through the parameters and return structure. However, it doesn't mention authentication requirements, rate limits, error conditions, or whether all parameters are required (though schema shows none are strictly required).

  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?

  The description is well-structured with clear sections: purpose statement, what information is provided, parameters with detailed explanations, and return structure. While comprehensive, it's appropriately sized for an 8-parameter tool with no schema descriptions. The parameter explanations are thorough but necessary given the context.

  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 8 parameters with 0% schema description coverage and no annotations, the description does an excellent job of explaining the tool's functionality. It covers purpose, parameters with semantics and examples, and the return structure. The main gap is the lack of usage guidance relative to sibling tools, but otherwise it's quite complete for a read-only data retrieval tool.

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

  Parameters5/5

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

  The description provides excellent parameter semantics beyond the 0% schema description coverage. It explains all 8 parameters with Korean descriptions, examples for most (sigungu_cd, bjdong_cd, bun, ji), and clarifies the pagination parameters with default values. This fully compensates for the complete lack of schema descriptions.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: '건축물대장 오수정화시설을 조회합니다' (retrieves building registry sewage treatment facility information). It specifies the resource (sewage treatment facilities) and what information is provided (treatment type, capacity, unit). However, it doesn't explicitly distinguish this tool from its many sibling tools that also retrieve building-related information.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. With 11 sibling tools that all retrieve building-related information, there's no indication of when this specific sewage treatment facility tool should be selected over other building information tools. No prerequisites, exclusions, or alternatives are mentioned.

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

• get_building_atch_jibun_infoA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly indicates this is a read-only operation ('조회합니다' - retrieves/reads) and describes the paginated nature of results through the page_no and num_of_rows parameters. However, it doesn't mention rate limits, authentication requirements, error conditions, or whether all parameters are required for successful queries. The description adds some behavioral context but leaves significant gaps.

  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?

  The description is well-structured with clear sections: purpose statement, what information is provided, parameter documentation, and return format. Each sentence earns its place by adding value. While comprehensive, it could be slightly more concise by combining some of the parameter explanations or using a table format, but the current structure is logical and 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 tool's complexity (8 parameters, no annotations, but has output schema), the description provides substantial context. The output schema exists, so the description appropriately focuses on explaining the return structure rather than duplicating it. The parameter documentation is thorough, and the purpose is clear. The main gap is the lack of usage guidelines and some behavioral aspects like error handling or authentication requirements.

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

  Parameters5/5

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

  The description provides excellent parameter semantics that fully compensate for the 0% schema description coverage. It explains each of the 8 parameters with Korean names, English translations, format examples, and default values. The schema only shows parameter names and types, while the description adds crucial context about what each parameter represents (e.g., '시군구코드' = city/county/district code, '5자리' = 5 digits) and how to format them.

  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: '건축물대장 부속지번을 조회합니다' (retrieves building register attached lot numbers). It specifies the exact resource (building register attached lot numbers) and provides details about the information returned (lot address, new address, register classification). This distinguishes it from siblings like get_building_title_info or get_building_floor_ouln_info which target different building register aspects.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. While it mentions what information is provided, it doesn't indicate scenarios where this specific attached lot number data is needed versus other building information tools. There's no mention of prerequisites, dependencies, or typical use cases for this particular data subset.

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

• get_building_jijigu_infoA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It indicates this is a read operation ('조회합니다' - retrieves) and describes pagination behavior (page_no, num_of_rows, total_count). However, it doesn't disclose authentication requirements, rate limits, error conditions, or whether all parameters are required. The return format is described but without details about error responses or edge cases.

  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?

  Well-structured with purpose statement, additional context about what information is provided, then clear Args and Returns sections. Every sentence adds value, though the Korean-only text might limit accessibility for non-Korean agents. The structure is logical and front-loaded with the core purpose.

  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 8 parameters with 0% schema coverage and no annotations, the description does an excellent job explaining parameters and return values. The output schema exists (Returns section), so the description appropriately focuses on semantics rather than structure. Missing elements include authentication requirements and error handling, but for a read-only query tool, this is reasonably complete.

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

  Parameters5/5

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

  With 0% schema description coverage, the description fully compensates by providing detailed parameter explanations with examples (sigungu_cd: '5자리, 예: 11110 = 서울 종로구'), clarifying data formats, lengths, and meanings. All 8 parameters receive clear semantic explanations beyond what the bare schema titles 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's purpose with specific verb ('조회합니다' - retrieves/consults) and resource ('건축물대장 지역지구구역' - building registry regional/district/zoning information). It distinguishes from siblings by focusing specifically on zoning classifications rather than other building attributes like addresses, floors, or prices.

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

  Usage Guidelines2/5

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

  No guidance is provided about when to use this tool versus alternatives. While the purpose is clear, there's no mention of prerequisites, when this tool is appropriate versus other building information tools, or any constraints on usage. The agent must infer usage from the parameter structure alone.

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

• get_building_recap_title_infoA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It implies this is a read-only operation through the Korean term '조회합니다' (retrieves/reads), but doesn't explicitly state safety characteristics. It does reveal pagination behavior through the page_no and num_of_rows parameters and return structure, but doesn't mention rate limits, authentication needs, or potential error conditions.

  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?

  The description is well-structured with clear sections: purpose statement, data returned, parameters, and return format. While comprehensive, it's efficient with minimal redundancy. The parameter explanations are detailed but necessary given the poor schema coverage. The front-loaded purpose statement immediately communicates the tool's function.

  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 complex tool with 8 parameters, 0% schema description coverage, no annotations, but with output schema, the description does an excellent job compensating. It explains all parameters thoroughly, describes the return structure in detail, and clarifies what data is returned. The main gap is lack of guidance on when to use this versus sibling tools, but otherwise provides substantial context.

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

  Parameters5/5

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

  With 0% schema description coverage (titles only provide parameter names without meaning), the description fully compensates by providing detailed parameter explanations in the Args section. Each parameter gets clear Korean descriptions with format examples (e.g., '시군구코드 (5자리, 예: 11110 = 서울 종로구)'), making the 8 parameters fully understandable despite the schema's lack of 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 specific action ('조회합니다' - retrieves/reads) and resource ('건축물대장 총괄표제부' - building registry comprehensive title information), and provides a detailed list of the specific information returned. It distinguishes itself from siblings by focusing on comprehensive title information rather than specific aspects like floor outlines, house prices, or exposure information.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus the many sibling tools (11 alternatives). It doesn't explain what differentiates this comprehensive title information from other building registry queries, nor does it mention prerequisites, required parameters, or typical use cases for this specific data.

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

• get_building_expos_infoA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by: 1) Clearly indicating this is a read-only query operation ('조회합니다'), 2) Describing pagination behavior with page_no and num_of_rows parameters, 3) Specifying the return structure including pagination metadata. It doesn't mention rate limits or authentication requirements, but covers core behavioral aspects adequately.

  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?

  Well-structured with purpose statement, scope clarification, filtering capability note, and organized parameter/return sections. The Korean-only text may limit accessibility, but within that constraint, it's efficiently organized with no redundant information.

  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?

  Given 10 parameters with no schema descriptions, an output schema exists, and no annotations, the description provides complete context: purpose, parameter meanings with examples, filtering capabilities, pagination behavior, and return structure. It adequately compensates for all gaps in structured data.

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

  Parameters5/5

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

  With 0% schema description coverage, the description fully compensates by providing: 1) Korean translations and meanings for all 10 parameters, 2) Format examples (5-digit codes, 4-digit bun/ji), 3) Filtering explanations for dong_nm and ho_nm, 4) Default values for page_no and num_of_rows. This adds substantial value beyond the bare 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 tool's purpose: '건축물대장 전유부를 조회합니다' (retrieves building register exclusive use information). It specifies the exact resource (building register exclusive use part) and distinguishes from siblings by focusing on specific address and unit information rather than other building aspects like floor outlines, prices, or titles.

  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 through parameter explanations (filtering by dong/ho) but doesn't explicitly state when to use this tool versus alternatives. It mentions filtering capabilities but doesn't compare to sibling tools like 'get_building_title_info' or 'search_bjdong_code' for different use cases.

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

• search_bjdong_codeA
  4.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It mentions the tool is for '빠르게 찾습니다' (quickly find), suggesting efficiency, but lacks details on rate limits, error handling, or authentication needs. It doesn't contradict annotations (none exist), but provides minimal behavioral context beyond basic purpose.

  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 concise sentences with zero waste: the first states the purpose, the second provides usage guidelines. It's front-loaded with essential information and appropriately sized for the tool's complexity.

  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 1 parameter, no annotations, and an output schema (which handles return values), the description is reasonably complete. It covers purpose, usage, and parameter semantics, but could improve by adding more behavioral details (e.g., response format hints). The output schema reduces the need for return value explanation.

  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?

  The input schema has 1 parameter with 0% description coverage. The description adds semantic context by explaining that the 'query' parameter should be a '지역명(예: 강동구 고덕동)' (region name, e.g., Gangdong-gu Godeok-dong), clarifying it's for location names rather than codes or other inputs. This compensates well for the low schema coverage.

  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: '검색하여 빠르게 찾습니다' (search and quickly find) for '시군구코드(sigungu_cd) 및 법정동코드(bjdong_cd)' using '지역명(예: 강동구 고덕동)' (region name). It specifies the exact resource (codes) and verb (search/find), distinguishing it from sibling tools that retrieve building information rather than codes.

  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 provides explicit usage guidelines: '사용자의 주소 관련 질의에 대해 본 API를 호출하기 전에 코드를 획득하기 위해 반드시 이 툴을 먼저 사용하세요' (For user address-related queries, you must use this tool first to obtain codes before calling the main API). It specifies when to use (before API calls for address queries) and implies alternatives (the main API tools listed as siblings).

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

• get_building_expos_pubuse_area_infoA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden of behavioral disclosure and does so comprehensively. It reveals important behavioral traits: parameter normalization behavior ('hoNm은 "401호" 또는 "401" 모두 가능합니다' - hoNm accepts both formats with internal normalization), pagination behavior with default values, and specific parameter requirements. It also describes the return structure in detail, going beyond what the output schema would provide alone.

  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?

  The description is well-structured with clear sections: purpose statement, important guidelines, parameter details, and return format. While comprehensive, it could be slightly more concise - some information in the Args section repeats what's in the guidelines. However, every sentence adds value, and the front-loaded important guidelines ensure critical information is seen first.

  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 complex tool with 9 parameters, 0% schema description coverage, and no annotations, the description provides complete context. It covers purpose, usage constraints, parameter semantics with examples, behavioral details (normalization, pagination defaults), and return structure. Even with an output schema existing, the description adds valuable context about what '전유공용면적 정보' (exclusive/shared area information) contains in practical terms.

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

  Parameters5/5

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

  With 0% schema description coverage (titles only provide parameter names without meaning), the description fully compensates by providing extensive parameter semantics. Each parameter gets detailed explanations with examples: sigungu_cd is explained as '시군구코드 (5자리, 예: 11110 = 서울 종로구)' (municipality code, 5 digits, example). It clarifies parameter relationships (address components must be used together) and formatting rules for dong_nm and ho_nm.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: '건축물대장 전유공용면적을 조회합니다' (Retrieve building register exclusive/shared area information). It specifies the resource (building register exclusive/shared area) and action (retrieve/query). However, it doesn't explicitly differentiate from sibling tools like 'get_building_expos_info' or 'get_building_floor_ouln_info' which might retrieve related building information.

  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 provides excellent usage guidelines with explicit '중요/MCP 지침' (Important/MCP Guidelines) section. It clearly states when NOT to use certain parameters ('mgmBldrgstPk를 공식 파라미터로 지원하지 않습니다' - does not support mgmBldrgstPk as official parameter) and provides specific formatting rules for hoNm and dongNm parameters. It gives concrete examples for parameter values, making it very clear how to use this tool correctly.

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

• get_building_floor_ouln_infoA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes critical behavioral traits: the data mixing risk with multi-building complexes, pagination behavior (page_no, num_of_rows parameters), and the return format. However, it doesn't mention rate limits, authentication requirements, or error handling scenarios.

  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?

  The description is well-structured with clear sections: purpose statement, important guidelines, parameter explanations, and return format. While comprehensive, it could be more concise - some guideline details could potentially be streamlined. Every sentence adds value, but the overall length is substantial for a tool description.

  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?

  Given the complexity (8 parameters, no schema descriptions, no annotations) and the presence of an output schema, the description is remarkably complete. It covers purpose, critical usage guidelines, detailed parameter semantics, and behavioral considerations. The output schema handles return values, so the description appropriately focuses on usage context rather than repeating return structure.

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

  Parameters5/5

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

  With 0% schema description coverage, the description fully compensates by providing detailed parameter semantics. Each parameter is explained with examples (sigungu_cd: 11110 = Seoul Jongno-gu), format requirements (5-digit codes), and critical usage notes (mgm_bldrgst_pk is mandatory for multi-building complexes to avoid data mixing). Default values are also specified for page_no and num_of_rows.

  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: '건축물대장 층별개요를 조회합니다' (retrieves building register floor overview). It specifies the exact resource (building register floor information) and distinguishes it from siblings by focusing on floor-specific details like 층구분, 층번호, 구조, 용도, 면적 (floor classification, floor number, structure, purpose, area).

  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 provides explicit guidance on when and how to use this tool. It warns about data mixing issues with multi-building complexes and specifies that mgm_bldrgst_pk is mandatory for such cases. It also directs users to sibling tools (smart_building_lookup, get_building_title_info) to obtain necessary parameters and explicitly tells users not to search terminal logs but to call APIs properly.

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

• get_building_title_infoA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden. It effectively discloses key behavioral traits: it's a read-only operation (조회합니다), requires specific input validation (correct codes), has pagination behavior (page_no, num_of_rows), and returns structured data. It doesn't mention rate limits or authentication needs, but covers essential operational constraints well.

  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?

  The description is well-structured with clear sections: purpose statement, important guidelines, data returned, parameters, and return format. While comprehensive, some redundancy exists (e.g., listing parameters in both description and Args section). Every sentence adds value, but it could be slightly more streamlined.

  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?

  Given the tool's complexity (8 parameters, no annotations) and the presence of an output schema, the description is complete. It explains the tool's purpose, usage constraints, parameter semantics, and return structure. The output schema details the return format, so the description appropriately focuses on operational context rather than repeating return value details.

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

  Parameters5/5

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

  With 0% schema description coverage, the description fully compensates by providing detailed parameter explanations. It defines all 8 parameters with examples (e.g., '11110 = 서울 종로구'), format requirements (5자리, 4자리), and default values (page_no: 1, num_of_rows: 100). This adds significant meaning beyond the bare 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 tool's purpose: '건축물대장 표제부를 조회합니다' (retrieves building registry title information). It specifies the exact resource (building registry title) and distinguishes it from siblings by listing the specific information it provides (address, area, structure, usage, etc.), unlike other tools that focus on different building aspects like floor plans or house prices.

  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 provides explicit usage guidance: it mandates using correct codes from 'search_bjdong_code' and prohibits checking terminal logs if results are empty. It also implicitly distinguishes this tool from siblings by listing the specific data it returns, helping users choose it over alternatives like 'get_building_floor_ouln_info' or 'get_building_house_price_info'.

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

• smart_building_lookupA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains the tool's automatic processing flow: distinguishing between general and collective buildings, what data is returned for each type, and what is excluded (e.g., not retrieving '전유부' for collective buildings). It also details post-return AI actions, including user interaction steps and specific tool calls for follow-ups, providing comprehensive behavioral context beyond basic functionality.

  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?

  The description is well-structured with clear sections (purpose, usage guidelines, processing flow, post-return instructions, and parameters), making it easy to parse. It is appropriately detailed for a complex tool but could be slightly more concise in the post-return instructions, which include multiple sentences and warnings. Overall, most sentences earn their place by providing essential guidance.

  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?

  Given the tool's complexity (5 parameters, no annotations, but with an output schema), the description is highly complete. It covers purpose, prerequisites, detailed behavioral flow, post-return AI actions, and parameter semantics. The output schema likely handles return values, so the description appropriately focuses on usage context and workflow integration, making it sufficient for effective tool selection and invocation.

  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 description coverage is 0%, so the description must compensate. It lists all 5 parameters in the Args section with brief explanations (e.g., '시군구코드 (5자리, search_bjdong_code로 조회)' - Sigungu code (5 digits, lookup with search_bjdong_code)), adding meaning beyond the schema's titles. However, it doesn't fully explain parameter interactions or provide examples for all parameters (e.g., detailed format for 'bun'), leaving some gaps in semantic clarity.

  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: '건축물대장 스마트 조회 — 주소 하나로 건축물 전체 개요를 자동으로 파악합니다' (Smart building register lookup — automatically grasp the entire overview of a building with one address). It specifies the verb ('조회' - lookup), resource ('건축물대장' - building register), and scope ('전체 개요' - entire overview), distinguishing it from siblings that focus on specific parts like '전유부' or '층별 정보'.

  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 provides explicit guidance on when to use this tool: '이 도구는 사용자가 건축물대장을 조회할 때 가장 먼저 호출해야 하는 핵심 도구입니다. search_bjdong_code로 코드를 얻은 뒤 이 도구를 호출하세요' (This tool is the core tool that should be called first when a user looks up a building register. Call this tool after obtaining codes with search_bjdong_code). It names the prerequisite tool (search_bjdong_code) and positions this as the initial step in a workflow, clearly differentiating it from sibling tools used later for specific details.

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