Server Quality Checklist

Tool Scores

• lifeguard_get_statusA
  3.9/5.0
  Behavior4/5

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

  Annotations already mark it read-only and idempotent. Description adds conditional behavior (bed info only if active session) and return fields. No contradictions, but edge cases not covered.

  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 main purpose first, conditional behavior, then args/returns in a list. Concise, slightly verbose in the returns section but still 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 one optional parameter, no output schema, the description covers purpose, parameter behavior, and return values. Lacks error handling info, but rest is sufficient.

  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?

  Single parameter session_id is described in both schema and description identically. Schema coverage is 100% so baseline 3 applies; description adds no new semantics beyond restating.

  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 it queries emergency mode status and optionally retrieves real-time bed info. It distinguishes from siblings by using specific verb(조회) and resource(응급 모드 상태).

  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?

  Parameter usage is explained (session_id optional, defaults to latest). No explicit guidance on when to use this tool vs. siblings or when not to use it. Adequate but not explicit.

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

• lifeguard_search_emergencyA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, which align with the read-only search nature. The description adds behavioral details beyond annotations, such as real-time data integration, scoring formula, and the top 5 result limitation.

  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 well-structured with sections for Args, Returns, and Examples. It is front-loaded with the purpose and every sentence adds value. There is no fluff.

  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 (5 parameters, no output schema), the description explains the return structure (top 5 hospitals, symptom analysis, scoring explanation) and provides examples. However, it lacks error handling or edge cases (e.g., no hospitals found).

  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 100%, so baseline is 3. The description adds value with examples (e.g., '가슴통증', '소아고열') and contextualizes parameters like response_format, improving understanding beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool recommends optimal emergency medical institutions based on symptoms and current location, using specific criteria. It is distinct from sibling tools like lifeguard_activate_emergency (activation) and lifeguard_find_pharmacy (pharmacy).

  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 context and examples but does not explicitly state when not to use this tool or compare with siblings. Usage is implied through examples but lacks explicit guidance on alternatives.

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

• lifeguard_find_pharmacyA
  4.4/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, openWorldHint, etc. Description adds behavioral details such as default filter and radius, return format options, and the nature of results (list of pharmacies with fields). This is valuable beyond annotations.

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

  Conciseness4/5

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

  Description is well-structured with clear sections for args and examples, front-loading the main purpose. It is moderately concise and each sentence adds value.

  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?

  Despite no output schema, the description specifies the return structure (list of pharmacies with name, address, phone, distance, hours). Examples cover typical use cases. For a search tool with 6 parameters, this is 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?

  Schema description coverage is 100%, so baseline is 3. Description adds natural language explanations, default values, and examples for parameters like filter and response_format, improving understanding beyond 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?

  Description states '주변 약국을 검색합니다.' which is a specific verb and resource. It clearly distinguishes from sibling tools like lifeguard_get_status and lifeguard_search_emergency by focusing on pharmacies.

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

  Usage Guidelines4/5

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

  Description provides context for when to use (finding nearby pharmacies with optional filters) and includes examples. However, it does not explicitly exclude other tools or compare to alternatives.

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

• lifeguard_activate_emergencyA
  4.6/5.0
  Behavior5/5

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

  Annotations indicate readOnlyHint=false (write operation) and destructiveHint=false. The description adds behavioral context: it activates emergency mode, triggers movement, sends alerts, and starts monitoring. No contradictions with annotations.

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

  Conciseness4/5

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

  The description is somewhat long but well-structured with sections: purpose, action list, args, returns, example. It is front-loaded with the main action, and each sentence adds value, though it could be slightly more concise.

  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?

  All 7 parameters are fully described, and despite no output schema, the description lists return values (session info, deep link, alert result, monitoring info, tips). Given the context signals (no enums, no nested objects), the description is complete and informative.

  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 100%, so baseline is 3. The description adds extra value by explaining each parameter in detail (e.g., hospital_id sourced from search results, notify_guardians default true) and providing examples, raising the 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 '응급 모드를 활성화합니다' (activates emergency mode) and details specific actions: starting hospital movement, sending KakaoTalk alert, and beginning real-time bed monitoring. It is distinct from sibling tools like lifeguard_search_emergency (search) and lifeguard_get_status (status check).

  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 specifies that this tool should be called after selecting a hospital from lifeguard_search_emergency, providing clear when-to-use guidance. It does not explicitly state when not to use or alternatives, but the context is sufficient.

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