Server Quality Checklist

Tool Scores

• buildApplicationTimelineC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool creates a timeline but doesn't describe what the output looks like (e.g., format, structure), whether it's a one-time generation or editable, or any side effects like saving data. For a tool with no annotations and no output schema, this leaves significant gaps in understanding its behavior.

  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 concise and front-loaded, stating the core function in a single sentence. It uses efficient language without redundancy, though the inclusion of '【일정 관리】' (schedule management) as a tag adds slight noise. Overall, it's 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.

  Completeness2/5

  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, no output schema), the description is incomplete. It doesn't explain the output format or behavioral details, leaving the agent uncertain about what to expect. Without annotations or output schema, the description should provide more context on how the timeline is generated and presented, but it falls short.

  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 80%, providing a solid baseline. The description adds minimal value beyond the schema, as it doesn't explain parameter meanings or interactions (e.g., how 'deadline' drives the reverse calculation, or the role of 'projectPeriodMonths'). It implies a process flow but doesn't clarify parameter semantics, so it meets the baseline for high schema coverage without compensation.

  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: '역산 타임라인을 생성합니다' (creates a reverse timeline) for the application process from document collection to submission. It specifies the resource (application timeline) and verb (create), though it doesn't explicitly differentiate from sibling tools like 'draftBusinessPlan' or 'generateDocumentChecklist' which might have overlapping domains.

  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 mentions the process flow but doesn't specify prerequisites, exclusions, or compare it to siblings like 'checkEligibility' or 'draftBusinessPlan' that might be related to application preparation. Usage is implied by the context of managing deadlines, but no explicit instructions are given.

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

• compareByRegionC
  2.9/5.0
  Behavior2/5

  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 mentions the tool returns a comparison table and top announcements list, but doesn't describe important behavioral aspects like whether this is a read-only operation, what format the returns take, whether there are rate limits, authentication requirements, or how results are sorted/filtered beyond the parameters.

  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 appropriately concise with two sentences that efficiently convey the core functionality. The first sentence explains what the tool does, and the second describes what it returns. There's no unnecessary verbiage, though it could be slightly more structured for clarity.

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

  Completeness2/5

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

  For a tool with 5 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain the return format, how results are presented in the comparison table, what 'top announcements' means, or important behavioral constraints. The description leaves too much undefined for proper agent understanding.

  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 5 parameters thoroughly. The description doesn't add meaningful semantic context beyond what's in the schema - it mentions comparing regions and filtering by field, but the schema already describes regions, field enum values, keyword filtering, maxPerRegion defaults, and source options with clear 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 compares government support announcements across regions, listing number of announcements and field distribution, and returns a comparison table and top announcements. It specifies the resource (government support announcements) and action (compare by region), but doesn't explicitly differentiate from sibling tools like searchGovernmentSupport or other search tools.

  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 the tool does, it doesn't indicate when this comparison functionality is appropriate versus using search tools, eligibility checks, or other sibling tools for different purposes.

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

• draftBusinessPlanC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool generates a structured draft with section guides and item lists, which implies a creative/writing operation. However, it lacks details on permissions needed, rate limits, output format (e.g., text, JSON), whether it's idempotent, or error handling. For a tool with no annotations and complex inputs, this is a significant gap.

  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 concise and front-loaded, with two sentences that directly state the purpose and output features. There's no wasted text, and it efficiently communicates the core functionality. However, it could be slightly more structured by separating usage context from output details.

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

  Completeness2/5

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

  Given the complexity (6 parameters, nested objects, no output schema, and no annotations), the description is incomplete. It explains the high-level function but lacks details on behavioral traits, parameter usage, and output expectations. For a tool that generates structured documents, more context on the output format and process is needed to be fully helpful.

  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 description mentions analyzing '공고 텍스트와 회사 정보' (announcement text and company information), which aligns with parameters like 'announcementText' and 'companyProfile'. However, schema description coverage is 50%, and the description doesn't add meaning for undocumented parameters (e.g., 'announcementTitle', 'businessNumber', 'requestedAmount', 'projectPeriodMonths') or clarify usage. It provides marginal context but doesn't fully compensate for the coverage gap.

  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: '공고 텍스트와 회사 정보를 분석해 사업계획서 구조화 초안을 생성합니다' (analyzes announcement text and company information to generate a structured draft business plan). It specifies the verb (analyze and generate), resource (business plan draft), and scope (structured with sections). However, it doesn't explicitly differentiate from sibling tools like 'draftSettlementReport' or 'generateDocumentChecklist', which might also generate documents.

  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 mentions what it does but doesn't specify prerequisites, ideal scenarios, or exclusions. For example, it doesn't indicate if this should be used before or after tools like 'checkEligibility' or 'searchGovernmentSupport', or if it's for initial drafting versus finalization.

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

• manageBenefitHistoryC
  2.9/5.0
  Behavior2/5

  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 but provides minimal information. It mentions the available actions but doesn't describe what each action does behaviorally (e.g., whether 'delete' is permanent, whether 'create' requires specific permissions, what format results return, or any rate limits). The description doesn't contradict annotations since none exist, but it fails to provide essential behavioral context for a multi-action tool with 16 parameters.

  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 reasonably concise with two sentences that cover the tool's purpose and available actions. The action list is efficiently presented. However, the Korean text followed by English action list creates minor structural inconsistency, and the description could be more front-loaded with critical information about the tool's primary use cases.

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

  Completeness2/5

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

  For a complex tool with 16 parameters, no annotations, no output schema, and multiple actions, the description is inadequate. It doesn't explain the relationships between actions and parameters, doesn't describe return formats, and provides no behavioral context. The description fails to address the tool's complexity, leaving significant gaps in understanding how to use it effectively.

  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?

  With 56% schema description coverage, the description adds minimal value beyond what the schema provides. It mentions the available actions but doesn't explain when each parameter is required or how they interact with different actions. The schema already documents most parameters adequately, so the baseline of 3 is appropriate, but the description doesn't compensate for the 44% coverage gap in parameters like 'companyName', 'announcementId', or 'memo'.

  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: managing government support benefit history with specific operations like business selection registration, expense addition, and milestone recording. It distinguishes itself from siblings by focusing on historical data management rather than eligibility checking, searching, or document generation. However, it doesn't explicitly contrast with similar-sounding tools like 'searchGovernmentSupport'.

  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 lists available actions, it doesn't explain when to choose 'list' versus 'get', or when to use this tool instead of sibling tools like 'searchGovernmentSupport' or 'checkEligibility'. There's no mention of prerequisites, dependencies, or typical workflow contexts.

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

• search_gov_support_smes24C
  2.9/5.0
  Behavior2/5

  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 mentions authentication requirements (API key and IP allowance), which is useful. However, it lacks details on rate limits, error handling, response format, or whether the operation is read-only or has side effects. For a tool with no annotations, this leaves significant gaps in understanding its behavior.

  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 brief and to the point, consisting of two sentences that cover the core functionality and prerequisites without unnecessary elaboration. It is front-loaded with the main action. However, it could be slightly more structured by separating usage notes from the core purpose for better clarity.

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

  Completeness2/5

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

  Given the complexity (a search tool with four parameters, no output schema, and no annotations), the description is incomplete. It lacks details on output format, error conditions, pagination behavior, and differentiation from sibling tools. While it covers authentication needs, it doesn't provide enough context for an agent to use the tool effectively without additional assumptions.

  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 50% (two of four parameters have descriptions in the schema). The description does not add any information about parameters beyond what the schema provides, such as explaining the purpose of 'pageNo' and 'numOfRows' for pagination or detailing date format constraints. With moderate schema coverage, the baseline score of 3 reflects that the description doesn't compensate for the gaps but doesn't worsen them either.

  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 action ('단독 조회합니다' - 'retrieves individually') and the resource ('중소벤처24 공고 API(extPblancInfo)' - 'SME Venture 24 announcement API'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'searchGovernmentSupport' or 'search_gov_support_bizinfo', which likely serve similar purposes but target different resources or APIs.

  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 mentions prerequisites ('SMES24_API_KEY 및 서버 IP 허용이 필요합니다' - 'requires SMES24_API_KEY and server IP allowance'), which provides some context for when to use it. However, it offers no guidance on when to choose this tool over alternatives like 'searchGovernmentSupport' or 'search_gov_support_bizinfo', nor does it specify exclusions or ideal scenarios for its use.

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

• search_gov_support_kstartupB
  3.1/5.0
  Behavior2/5

  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 mentions the authentication requirement (PUBLIC_DATA_SERVICE_KEY), which is valuable context. However, it lacks critical behavioral details such as whether this is a read-only operation, potential rate limits, pagination behavior (implied by pageNo/numOfRows but not explained), error handling, or what the output format looks like. The description is insufficient for a tool with 5 parameters and no output schema.

  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 appropriately concise with two sentences: one stating the purpose and resource, and another noting the authentication requirement. It's front-loaded with the core functionality. No wasted words, though it could be slightly more structured (e.g., separating purpose from prerequisites).

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

  Completeness2/5

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

  Given the complexity (5 parameters, no annotations, no output schema), the description is incomplete. It covers authentication and high-level purpose but misses behavioral traits (e.g., read-only status, pagination), output details, and guidance on parameter use. For a search tool with multiple filters and pagination, this leaves significant gaps for an AI agent to operate effectively.

  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 60% (3 of 5 parameters have descriptions: supt_biz_clsfc, supt_regin, rcrt_prgs_yn), while pageNo and numOfRows lack descriptions. The description adds no parameter-specific information beyond what the schema provides—it doesn't explain parameter interactions, default values beyond rcrt_prgs_yn's 'Y', or usage examples. With moderate schema coverage, the baseline is 3 as the description doesn't compensate for the gaps.

  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 action ('단독 조회합니다' - retrieves/single query) and resource ('K-Startup(k-startup.go.kr) 창업지원사업 공고' - K-Startup startup support project announcements). It distinguishes from siblings like 'searchGovernmentSupport' by specifying the specific K-Startup platform, though it doesn't explicitly contrast with 'search_gov_support_bizinfo' or 'search_gov_support_smes24' which likely target different data sources.

  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 context by mentioning the required environment variable (PUBLIC_DATA_SERVICE_KEY) for authentication, which suggests when this tool is applicable (when that key is available). However, it provides no explicit guidance on when to use this tool versus sibling tools like 'searchGovernmentSupport', 'search_gov_support_bizinfo', or 'search_gov_support_smes24', leaving the agent to infer based on platform names.

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

• generateDocumentChecklistB
  3.2/5.0
  Behavior2/5

  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. While it describes the core function, it lacks critical behavioral details: what format the checklist output takes, whether this is a read-only analysis or creates persistent data, error handling for malformed input, or any rate limits. For a tool with 4 parameters and no output schema, this leaves significant gaps in understanding how the tool behaves.

  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 a single, efficient Korean sentence that front-loads the core purpose. Every element serves a purpose: identifies the task, source material, and output attributes. While concise, it could potentially benefit from slightly more structure for non-Korean readers, but within the Korean context it's well-formed and waste-free.

  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?

  Given the tool's complexity (document extraction and checklist generation with 4 parameters), no annotations, and no output schema, the description is minimally adequate but incomplete. It covers the what but not the how or what results to expect. For a tool that presumably returns structured checklist data, the absence of output information is a significant gap, though the purpose is clearly stated.

  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%, providing good parameter documentation. The description adds marginal value by contextualizing the parameters as coming from '공고 텍스트' (announcement text), but doesn't provide additional semantics beyond what's in the schema. It doesn't explain relationships between parameters or provide usage examples. Baseline 3 is appropriate given the comprehensive schema coverage.

  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: extracting required documents from announcement text and generating a checklist with specific attributes (issuing authority, processing time, collection deadline). It uses specific verbs ('추출하다' - extract, '생성하다' - generate) and identifies the resource (documents from announcements). However, it doesn't explicitly differentiate from sibling tools that might also process announcement data.

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

  Usage Guidelines3/5

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

  The description implies usage context by mentioning '공고 텍스트' (announcement text) and document preparation, suggesting it's for processing government/business announcements. However, it provides no explicit guidance on when to use this tool versus alternatives like 'checkEligibility' or 'searchGovernmentSupport', nor does it mention any prerequisites or exclusions.

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

• checkEligibilityB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but lacks critical behavioral details. It mentions returning status and recommendations but does not disclose authentication requirements, rate limits, data handling (e.g., profile merging), or whether the analysis is deterministic or AI-based. This leaves significant gaps for safe and effective tool invocation.

  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 concise and front-loaded, stating the core purpose in a single sentence. However, the inclusion of Korean characters (【자격 판정】) adds minor redundancy without functional value, slightly detracting from efficiency.

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

  Completeness3/5

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

  For a complex tool with 6 parameters, nested objects, and no output schema, the description is moderately complete. It covers the high-level purpose but lacks details on output structure, error handling, and behavioral constraints. Without annotations or output schema, the agent has insufficient context for reliable use.

  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%, providing detailed parameter documentation. The description adds minimal value beyond the schema, only implicitly referencing 'announcement text' and 'company profile' without explaining parameter interactions or the merging logic for saved profiles. Baseline 3 is appropriate given the schema's comprehensive 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: analyzing announcement text and company profiles to determine eligibility for support. It specifies the verb ('analyze'), resources ('announcement text and company profile'), and output ('eligibility fulfillment status with recommendations'), distinguishing it from sibling tools like search or draft functions.

  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 context (evaluating eligibility for government support) but does not explicitly state when to use this tool versus alternatives like searchGovernmentSupport or compareByRegion. No exclusions or prerequisites are mentioned, leaving the agent to infer appropriate scenarios.

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

• search_gov_support_bizinfoB
  3.4/5.0
  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 of behavioral disclosure. It mentions the need for an API key (authentication requirement) and implies search functionality, but it doesn't describe key behaviors such as rate limits, pagination details (beyond what's in the schema), error handling, or the format of returned data. For a search tool with no annotations, this leaves significant gaps in transparency.

  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 concise and front-loaded, with two sentences that efficiently state the purpose, search capability, and authentication requirement. There's no wasted text, and it's appropriately sized for the tool's complexity. However, it could be slightly more structured (e.g., separating usage notes) to reach the highest score.

  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?

  Given the tool's moderate complexity (search with pagination), no annotations, and no output schema, the description is incomplete. It covers the basic purpose and authentication but lacks details on behavioral traits (e.g., rate limits), output format, and differentiation from siblings. For a tool without structured output documentation, more context is needed to be fully helpful to an AI agent.

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

  Parameters3/5

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

  The input schema has 100% description coverage, providing clear details for all parameters (field, pageIndex, pageUnit) including enums and defaults. The description adds minimal value beyond the schema, only implying field-based search without specifying syntax or additional constraints. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't significantly enhance parameter understanding.

  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: '기업마당(bizinfo.go.kr) 지원사업 공고를 단독 조회합니다' (retrieves government support announcements from bizinfo.go.kr). It specifies the resource (support announcements) and action (retrieve/search). However, it doesn't explicitly distinguish this tool from sibling tools like 'searchGovernmentSupport' or 'search_gov_support_kstartup', which appear to serve similar purposes, so it doesn't reach the highest clarity level.

  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 provides some usage context: '분야별 검색이 가능합니다' (field-based search is possible) and mentions the required BIZINFO_API_KEY environment variable. However, it doesn't explicitly state when to use this tool versus alternatives like 'searchGovernmentSupport' or 'search_gov_support_smes24', nor does it provide exclusions or detailed prerequisites beyond the API key. Usage is implied rather than explicitly guided.

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

• manageAlertProfileA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions CRUD operations but lacks details on permissions required, whether changes are reversible, rate limits, or what happens to existing data during updates/deletes. For a tool with multiple mutation actions (create, update, delete) and no annotations, this is a significant gap in transparency.

  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 concise and front-loaded, stating the core purpose in the first sentence and listing actions and condition types efficiently. It uses minimal sentences with no wasted words. However, the inclusion of Korean characters and mixed formatting slightly reduces readability, preventing a perfect score.

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

  Completeness2/5

  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, multiple mutation actions) and lack of annotations and output schema, the description is incomplete. It does not cover behavioral aspects like authentication needs, error handling, or response formats, which are crucial for an agent to use this tool effectively. The schema covers parameters well, but the description fails to compensate for missing context elsewhere.

  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 8 parameters thoroughly. The description adds minimal value beyond the schema by listing the condition types (keywords, fields, regions, target types) and specifying the action parameter values, but it does not provide additional syntax, format, or usage details for parameters. Baseline 3 is appropriate when the schema does the heavy lifting.

  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: managing alert profiles for government support notifications through CRUD operations (create, retrieve, update, delete). It specifies the resource ('alert profiles'), the actions, and the types of alert conditions stored (keywords, fields, regions, target types). This is specific and distinguishes it from sibling tools which focus on searching, drafting, or checking eligibility rather than profile management.

  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 context for when to use this tool: for managing alert profiles with specific condition types. It lists the available actions (list, get, create, update, delete), which helps guide usage. However, it does not explicitly state when NOT to use it or name alternatives among sibling tools (e.g., searchGovernmentSupport for finding supports vs. managing alerts).

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

• searchGovernmentSupportA
  4/5.0
  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 does well by describing the deduplication behavior and default source selection. However, it doesn't mention important behavioral aspects like rate limits, authentication requirements, pagination, error conditions, or what the unified result format looks like. For a complex 8-parameter search tool with no annotations, this 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 efficiently structured in two sentences that convey the core functionality and key capabilities. Every sentence earns its place by providing essential information about the tool's integrated search approach and parameter options. It could be slightly more front-loaded by mentioning the deduplication earlier, but overall it's well-structured.

  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?

  Given the tool's complexity (8 parameters, no annotations, no output schema), the description provides good context about the integrated search approach and deduplication. However, it doesn't explain the return format, error handling, or important behavioral constraints. For a search tool that aggregates multiple sources, more information about result structure and limitations would be helpful.

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

  Parameters3/5

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

  The schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description mentions keyword, field, region, and source selection capabilities, but adds no additional semantic context beyond what's already in the parameter descriptions. The baseline of 3 is appropriate when the schema does the heavy lifting.

  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 verbs ('통합 탐색', '동시에 검색', '중복 공고를 제거', '통합 결과를 반환') and resources ('기업마당·K-Startup·중소벤처24'). It explicitly distinguishes itself from sibling tools by mentioning it searches multiple sources simultaneously and removes duplicates, unlike the single-source search_gov_support_* tools.

  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 by stating it searches multiple sources simultaneously and removes duplicate announcements. It also specifies the default sources (bizinfo + kstartup) and mentions alternative sources can be selected, clearly differentiating it from the single-source sibling tools (search_gov_support_bizinfo, search_gov_support_kstartup, search_gov_support_smes24).

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

• draftSettlementReportA
  4.2/5.0
  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 mentions the tool creates a draft report, implying a write operation, but doesn't specify permissions, rate limits, or what the output looks like (e.g., format, structure). It adds some context about prerequisites, but lacks details on behavioral traits like error handling or side effects.

  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 appropriately sized and front-loaded, with the first sentence stating the core purpose and the second providing essential usage guidelines. Every sentence earns its place without redundancy, making it efficient and well-structured.

  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 (a report generation tool with 5 parameters and no output schema), the description is fairly complete. It explains the purpose, prerequisites, and key parameters implicitly, but lacks details on output format or error conditions. With no annotations and no output schema, it could benefit from more behavioral context, but it covers essential usage aspects adequately.

  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 parameters. The description adds minimal semantic value beyond the schema, mentioning the benefitRecordId as the basis but not elaborating on parameter interactions or usage nuances. Baseline 3 is appropriate as the schema handles most documentation.

  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 verbs ('생성합니다' - creates) and resources ('정산 보고서 초안' - settlement report draft), and distinguishes it from siblings by specifying it generates a draft report based on benefit history ID, unlike tools like manageBenefitHistory or add_expense which handle different operations.

  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, stating when to use this tool ('먼저 manageBenefitHistory 로 이력을 등록하고 지출(add_expense)을 기록한 후 사용하세요' - first register history with manageBenefitHistory and record expenses with add_expense, then use this) and naming alternatives (manageBenefitHistory, add_expense), which clarifies prerequisites and workflow context.

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