Server Quality Checklist

Tool Scores

• realestate_analyze_rent_ratioA
  3.5/5.0
  Behavior2/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so safety is known. However, the description adds no extra behavioral context such as data sources, output details, or limitations; it essentially restates the 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 concise, front-loaded with the main purpose, and followed by a clear argument list. Every sentence adds value without filler.

  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?

  The output schema and annotations cover return values and safety, but the description lacks operational context like region code vs. name and year_month format. It is adequate for a simple read-only tool but leaves gaps that might require clarification.

  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 description adds Korean meanings for all four parameters, compensating for 0% schema coverage. However, ambiguities remain, such as whether 'region' expects a name or code and the exact format of 'year_month' (e.g., YYYY-MM), preventing a perfect score.

  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 'analyzes the jeonse-to-sale price ratio' (매매가 대비 전세가율을 분석한다), indicating a specific verb and resource. This distinguishes it from sibling tools like price trend analysis or search tools, making the purpose unambiguous.

  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. It only lists arguments without discussing use cases, prerequisites, or exclusions relative to sibling tools.

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

• realestate_get_apt_summaryA
  3.5/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds the temporal scope ('최근 N개월' = recent N months) and response format options, providing some behavioral context, but does not disclose return structure 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.

  Conciseness5/5

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

  The description is a concise single sentence in Korean followed by an Args list. It front-loads the core action and includes necessary parameter constraints without any fluff or 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 an output schema exists and annotations cover read-only behavior, the description is mostly complete: it defines the scope (specific complex, time range, output format). However, it lacks guidance on selecting this over related tools, making it slightly incomplete for full contextual understanding.

  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 0%, so the description carries the burden. It explains all four parameters: region, apt_name, months with default and max, and response_format with default. This adds meaning beyond the bare schema names, though it lacks examples or valid value enums.

  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 provides comprehensive summary information for a specific apartment complex, using a specific verb and resource. It differentiates from siblings like search_apt_trade or analyze_price_trend by focusing on 'specific complex summary', though it does not explicitly name alternatives.

  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 given on when to use this tool versus alternatives like realestate_search_apt_trade or realestate_analyze_price_trend. The description only explains what the tool does, implying usage for summary queries but lacking explicit scenarios, exclusions, or comparisons.

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

• realestate_analyze_price_trendA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds no additional behavioral context such as prerequisites, data limitations, or response nuances, but does not contradict the 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?

  The description is concise: a single purpose sentence followed by a structured parameter list. Each parameter line includes a brief description and example, making it highly efficient and easy to parse.

  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 read-only analysis nature and the existence of an output schema, the description adequately covers the tool's purpose and all parameters. It does not mention prerequisites like needing to obtain a region code first, but the parameter examples and filter explanations make it reasonably complete.

  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 schema has 0% parameter descriptions, so the description's Args section compensates by explaining all six parameters, including examples for date format ('202301'), area range ('59-84'), and response_format options. This adds meaningful semantic detail beyond the schema, though it could be more precise about region/apt_name formats.

  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 analyzes price trends for a specific region or apartment complex, using a specific verb ('analyzes') and resource ('price trends'). It also distinguishes itself from sibling tools like transaction search and rent analysis by focusing on trend analysis over time.

  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 the tool is for analyzing price trends, but it does not explicitly state when to use it versus alternatives like realestate_search_apt_trade or realestate_compare_regions. No exclusion criteria or alternative guidance is provided.

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

• realestate_search_apt_rentA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds the query scope (region/period) but does not disclose pagination, rate limits, or error behavior beyond the basic operation.

  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 purpose sentence followed by a structured Args list. Each parameter is described efficiently, with no redundant 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?

  All parameters are documented with examples, and response_format options are noted. However, it does not mention prerequisite lookup via realestate_get_region_code or the meaning of openWorldHint, though the output schema likely covers 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 compensates by listing all 9 parameters with types and examples (e.g., '202401' for year_month, '전세'|'월세'|'전체' for rent_type). This adds essential semantics missing from 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 states a specific verb '조회한다' (retrieves) and resource '아파트 전월세 실거래가' (apartment jeonse/monthly rent transaction prices) with scope '특정 지역·기간'. This clearly differentiates it from sibling tools like realestate_search_apt_trade, which likely handles purchase transactions.

  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 for reviewing rental transaction data over a specific region and period, but it does not explicitly mention when-not-to-use or compare to alternative sibling tools. There is no exclusion guidance.

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

• realestate_compare_regionsA
  4.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds no extra behavioral context such as rate limits or data scope caveats, but does not contradict 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?

  The description is concise, front-loaded with the main purpose, and uses a clear Args block. Every sentence adds value without 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?

  Covers the core use case and all parameters, and an output schema exists so return values need no explanation. Minor gap: '시세' could ambiguously refer to sale or rent prices, but the overall context from sibling tools mitigates this.

  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?

  With 0% schema description coverage, the description compensates by explaining each parameter: regions (min 2 max 5), year_month (comparison basis), area_range (example filter), and response_format (default/options). It adds meaning beyond the schema, though year_month format is not specified.

  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 compares and analyzes market prices of 2 or more regions, which is a specific verb+resource+scope. This distinguishes it from sibling tools that handle single-region or specific transaction types.

  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 the tool is for multi-region comparison, making the use case clear. However, it does not explicitly mention when not to use it or name alternative tools, but the context is sufficiently distinct.

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

• realestate_search_apt_tradeA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare this as read-only, idempotent, and non-destructive. The description adds useful constraints (e.g., year_month or start/end required, response_format default) that are not enforced by the schema. No contradictions with annotations exist.

  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 compact and well-organized as a parameter list, with each line earning its place. It avoids fluff while covering all 8 parameters, though a brief note about return value could improve it.

  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) and that an output schema exists, the description adequately covers all parameter semantics and key constraints. Sibling differentiation could be more explicit, but the purpose is clear enough for an agent to select correctly.

  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 schema provides only parameter titles with no descriptions, so the Args list in the tool description fully compensates by explaining each parameter with examples, including the conditional requirement for date inputs. This adds high value over the structured 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 queries 'apartment sales actual transaction prices' for specific regions/periods. This distinguishes it from sibling tools like realestate_search_apt_rent, which handles rentals, and analysis tools like realestate_analyze_price_trend.

  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 apartment sales data is needed but does not explicitly contrast with alternatives like rental search or analysis tools. The requirement that year_month or start/end is mandatory is a parameter guideline, not a when-to-use statement.

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

• realestate_get_region_codeA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds useful context by mentioning fuzzy matching and providing example queries, which goes beyond the annotations and helps the agent understand input flexibility.

  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 and front-loaded with the main purpose, followed by a clear parameter explanation. Every sentence contributes value, and there is no redundant or filler content.

  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 single-parameter read-only lookup with an output schema, the description is largely sufficient. It covers purpose, parameter, and fuzzy matching. It does not detail how fuzzy matching handles ambiguity or whether multiple codes may be returned, but the output schema likely covers 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?

  The schema has zero description coverage for the 'query' parameter, but the description compensates fully with an Args section that explains the parameter as a region name search term and gives concrete examples. 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 explicitly states the action: look up legal dong code by region name, with a specific verb ('조회한다') and resource ('법정동 코드'). It also mentions fuzzy matching support, making it clearly distinct from sibling tools that focus on transactions and price analysis.

  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?

  Usage is implied rather than explicitly stated. The tool's purpose as a code lookup is clear, and siblings are all market-data tools, so when to use this is inferable; however, there is no explicit when/when-not guidance or alternative recommendations, which keeps it at a mid-level score.

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