Server Quality Checklist

Tool Scores

• get_clinical_sopA
  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 discloses what the tool returns (complete SOP, three views, evidence basis) but does not mention any side effects, permissions, or edge-case behavior. This is adequate for a query tool but lacks deeper behavioral context such as error handling or data scope.

  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, front-loaded sentence that efficiently conveys the tool's purpose and key features. Every word adds value, with no redundancy or filler.

  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 that an output schema exists, the description need not explain return values. The description covers the essential aspects: the object (SOP for warning rules), the views (doctor/nursing/parent), and evidence basis. It lacks explicit usage guidance, but the schema covers blank-rule_id behavior, making it sufficiently complete.

  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 already thoroughly covers the only parameter rule_id, including its default and blank behavior. The tool description adds no additional parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the tool queries the complete clinical SOP corresponding to warning rules, including doctor/nursing/parent views and evidence basis. This is a specific verb+resource that distinguishes it from sibling tools like evaluate_risk_rules and trigger_warning_event.

  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?

  While no explicit alternatives are named, the description clearly implies this tool is for retrieving SOPs for warning rules, which is distinct from the other sibling tools. The schema description also clarifies behavior when rule_id is blank. No exclusions are provided, but the context is clear enough.

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

• list_mock_patientsA
  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 full responsibility for behavioral disclosure. It describes the action as '列出' (list), which implies a read-only operation, and notes the mock nature of the data. However, it does not explicitly state that there are no side effects, require no special permissions, or describe any limitations. This is adequate for a simple listing tool but lacks deeper behavioral context.

  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, concise sentence that clearly communicates the tool's purpose and use case. There is no unnecessary information 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?

  The tool is simple with one optional parameter and an output schema, so the description is largely sufficient. It provides the purpose and usage context. It does not elaborate on return format, but the output schema exists, covering that. The only minor gap is not explicitly connecting the '全部' (all) in the description to the filtering capability of the scenario_type parameter, but the schema covers that.

  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 covers 100% of the parameter (scenario_type), so the description itself does not need to add parameter details. The tool description does not mention the parameter, but the schema fully documents its purpose and allowed values. Baseline 3 is appropriate since 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 function: '列出模拟 HIS 中全部可用患儿档案' (list all available pediatric patient records in the mock HIS). It uses a specific verb (list) and resource (patient records), and distinguishes itself from siblings like fetch_patient_biochemical_trends or evaluate_risk_rules by focusing on patient selection for demos.

  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 explicitly states the context: '用于 Demo 演示时选择研判对象' (used for selecting analysis targets during demo presentations). This implies when to use the tool but does not explicitly exclude alternative tools or mention when not to use it, so it's slightly below perfect.

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

• trigger_warning_eventA
  4.2/5.0
  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. It discloses key behaviors: pulling simulated LIS data, performing hard rule assessment, prioritizing the rule engine over agent_suggested_level, and recording level_correction in the receipt. It also mentions the return receipt with offset, providing useful transparency without contradictions.

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

  Conciseness4/5

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

  The description is appropriately sized, with a summary sentence, a flow diagram, and a behavioral note. It is front-loaded with the main purpose and every sentence adds value, though the flow could be slightly more compact.

  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 presence of an output schema and complete parameter descriptions, the description is sufficient. It explains the tool's role, the full process, and a critical correction behavior, leaving no major gaps in 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 coverage is 100%, so the baseline is 3. The description adds some context, especially for agent_suggested_level (used for consistency check and correction) and relates channels to delivery targets, but it does not systematically enrich parameter 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 generates structured warning messages, sends them to the northbound interface and message queue, and returns a delivery receipt. This is a specific verb+resource+outcome, and it is distinct from sibling tools like list_mock_patients or evaluate_risk_rules, which serve different functions.

  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 by outlining the complete flow (pull LIS data -> rule assessment -> assemble message -> deliver -> return receipt), which implies when the tool should be used. However, it does not explicitly specify when not to use it or name alternatives, so it lacks exclusions.

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

• evaluate_risk_rulesA
  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 the full burden. It discloses that arithmetic calculations are code-computed to prevent hallucination, that patient_id mode auto-fetches data, and that missing values are treated as missing. Also notes special handling for hemolyzed specimens. This offers valuable behavioral context beyond the 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 well-structured with a clear intro, rationale, and bulleted usage modes. It is slightly longer than necessary but every sentence contributes context. The front-loaded purpose statement helps the agent quickly identify the tool's role.

  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 10-parameter complexity and the presence of an output schema, the description sufficiently covers when and how to use the tool, return types (level and triggered rules), missing value behavior, and special cases. Additional details on exact thresholds are appropriately left to the SOP.

  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 already has 100% coverage with parameter descriptions. The description adds meaningful usage semantics by explaining the override behavior when patient_id is passed, the default handling for age/phosphorus in manual mode, and the special specimen_note trigger. This enhances 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 identifies the tool as a deterministic rule engine that evaluates against warning SOP hard thresholds, returning warning level and triggered rules. This specific verb-resource combination distinguishes it from sibling tools like fetch_patient_biochemical_trends or trigger_warning_event.

  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?

  Explicitly states two usage modes: passing patient_id for automatic LIS data pull (recommended) or direct metric values for manual entry. It also instructs the agent to rely solely on this tool's output for risk judgment. Does not explicitly contrast with alternatives, but context makes it clear.

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

• fetch_patient_biochemical_trendsA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It discloses the output contents (current results, baseline, change percentages, Z-scores) and reveals the mock nature and future data-source replacement, indicating it is a safe, read-only simulator. It does not explicitly state 'no side effects', but the fetch/simulation context makes this transparent.

  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?

  Two sentences, front-loaded with a label and immediate description of the resource. No filler words. The mock prefix and the data structure explanation are both purposeful.

  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 an output schema exists, the description needn't detail return values, but it does anyway, enhancing clarity. It addresses the tool's purpose, mock nature, and the fields included. The tool is simple (2 params) and this description 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?

  The schema describes both parameters (patient_id, months) with 100% coverage. The description does not add significant meaning beyond what the schema already states, though it connects 'months' to the historical baseline in the output. Baseline is 3 due to high 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 verb '获取' (fetch) and the resource '患儿生化指标趋势数据包' (pediatric biochemical trend data package). The '南向 Mock 工具' prefix distinguishes it as a mock LIS tool, differentiating it from sibling tools like list_mock_patients or evaluate_risk_rules.

  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 by stating it simulates the hospital LIS system and returns trend data, implying when to use it (when LIS trend data is needed). It does not explicitly name alternatives or exclusions, but sibling tools are clearly for different purposes. The schema references list_mock_patients as a prerequisite, hinting at a workflow.

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