Server Quality Checklist

Tool Scores

• get_diagnosisB
  3.3/5.0
  Behavior2/5

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

  Without annotations, the description carries full burden for behavioral disclosure. The verb '读取' (read) is largely tautological with the tool name and does not reveal additional traits such as authorization requirements (e.g., guardian_token), error behavior, or whether the operation is safe. No annotations exist to supplement this.

  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 clearly states the purpose. It is concise, contains no filler, and is appropriately sized for the tool's simplicity.

  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?

  With three parameters, no annotations, and an output schema, the description still omits essential context about guard_token semantics and how this tool fits with siblings. The brevity leaves gaps in usage guidance and security model, making it incomplete despite the output schema.

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

  Parameters1/5

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

  The input schema has 0% description coverage, and the description does not explain patient_id, caller, or guardian_token. The agent must guess parameter meanings from names alone, which is insufficient for correct invocation.

  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 reads the doctor-confirmed CKD stage and dialysis method, specifying the audience and purpose. It distinguishes itself from sibling tools like get_patient_profile and get_nutrition_ceiling by focusing on diagnosis data.

  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 context by stating it is intended for nutritionists and parent assistants to avoid re-calculating the stage, implying when to use it. However, it does not explicitly mention exclusions or compare with alternatives, so it falls just short of a 5.

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

• list_patientsA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the core behavior (searching by conditions and returning id list + summary) but does not address potential caveats such as default behavior when filters are absent, pagination, authentication, or rate limits. This is a moderate level of transparency for a read-oriented list 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, well-structured sentence that immediately conveys the action, target, criteria, and output. Every word earns its place, with no redundant information.

  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?

  An output schema exists, so the description need not detail return values. However, given the open-ended 'filter' object and lack of annotations, the description could provide more context on filter structure, pagination, or ordering. It is minimally sufficient but leaves several operational aspects unspecified.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate. It partially explains the 'filter' parameter by listing example attributes (age band, stage, dialysis modality), but it does not explain the 'caller' parameter or specify how the filter object should be structured. This leaves significant ambiguity for the agent.

  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: to search a pediatric patient cohort ('检索患儿队列') using criteria such as age band, stage, and dialysis modality, and to return a list of IDs with summaries. This distinguishes it from sibling tools that fetch individual profiles or perform verifications.

  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: use this tool when you need to retrieve a cohort of patients based on specific conditions like age band, stage, or dialysis modality. It does not explicitly mention alternatives or exclusion cases, but the context is clear enough for an agent to decide when to use it.

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

• verify_guardian_bindingA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the burden of behavioral disclosure. It does add context about the tool being a mandatory gate before data access, which is a useful behavioral trait. However, it does not disclose what happens on success/failure, whether it is read-only, or any security/error behavior. This is a minimum viable level of transparency.

  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 sentence that efficiently conveys purpose and mandatory usage. It is front-loaded with the core verb and resource, and every word contributes meaning. No filler or redundancy.

  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 description is adequate for a simple verification tool with an output schema, but it leaves gaps. It explains the tool's role as a prerequisite but does not mention failure behavior, return values, or exceptions. Given this is an access-control gate, understanding failure outcomes is important for correct invocation.

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

  Parameters2/5

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

  Schema description coverage is 0% and the description provides no explanation of the parameters 'patient_id' and 'guardian_token'. While the parameter names are somewhat self-explanatory given the tool's purpose, the description does not clarify token format, source, or relationship to the verification process. This fails to compensate for the lack of schema descriptions.

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

  Purpose5/5

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

  The description clearly states the tool's function: verifying the binding relationship between guardian and patient. It uses a specific verb '核验' (verify) and names the resource, distinguishing it from sibling data-access tools. The additional context that it is mandatory before patient data access further clarifies its unique role.

  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 when to use this tool: before every access to patient data by the parent assistant. This gives clear usage context but does not mention alternatives or exclusions. Since all siblings are data-access tools, it is implicit that this is the prerequisite step, but explicit when-not guidance is missing.

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

• get_nutrition_ceilingA
  3.9/5.0
  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 that this is a read operation ('读取') and that the data represents doctor-set limits, which implies authority. However, it does not mention any auth prerequisites (e.g., guardian_token), behavior when data is missing, or rate limits, leaving some behavioral aspects undisclosed.

  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, focused sentence that front-loads the action and purpose. 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?

  For a simple read-only tool with an output schema, the description is largely complete. It states what is returned (the six limits) and why it matters (as constraints for nutrition/recipes). It lacks explicit mention of preconditions or error handling, but these are less critical given the tool's simplicity and the existence of an output schema.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description provides no parameter-level guidance. While parameter names like patient_id and caller are somewhat self-explanatory, guardian_token and the exact role of caller remain unexplained. The description adds nothing beyond what the schema already exposes, and does not compensate for the low schema coverage.

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

  Purpose5/5

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

  The description clearly states the tool reads doctor-defined upper limits for six specific nutrients and fluids, and it positions this as a hard constraint for nutrition calculation and recipe generation. This is a specific verb+resource combination that clearly distinguishes it from sibling tools like get_patient_profile or get_diagnosis.

  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: the tool is to be used when performing nutrition calculations or generating recipes, where these limits act as hard constraints. It does not explicitly exclude other scenarios or name alternatives, but the usage context is unambiguous.

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

• get_patient_profileA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description fully carries the transparency burden. It discloses key behavioral traits: role-based data redaction (full view vs no biochemistry vs parent-limited), inclusion of 5-day diet diary and cross-month biochemistry in full view, and the mandatory guardian_token for parent access. This goes beyond typical descriptions and directly informs the agent of access-control behavior.

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

  Conciseness5/5

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

  The description is two sentences: the first gives the purpose and core content in a compact list, the second details view variations. No fluff, all sentences carry information, and the key purpose is front-loaded.

  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, return values are covered. The description explains the role-based view variations, which is essential for using this tool correctly. It also mentions the inclusion of diet diary and biochemistry in the full view, which are important contextual details not inferable from schema or annotations. The description is complete for the tool's complexity.

  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 must compensate. It explicitly explains that 'caller' determines the view and that 'guardian_token' is required for the parent view. Patient_id is not described but is self-evident from schema/name. This adds meaningful semantics for two of three parameters, but leaves patient_id implicit, so it is not a full compensation.

  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 starts with a specific verb+resource: '读取患儿档案' (read patient profile) and enumerates the contained fields (demographics, diagnosis stage, etiology, dialysis modality, allergies, nutrition ceiling). This clearly distinguishes it from siblings like get_diagnosis (single diagnosis) or get_nutrition_ceiling (only the ceiling) by presenting the full profile scope.

  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 role-based context for when to use the tool, listing which callers (doctor assistant, risk warning, dispatch, nutritionist, parent) get which views and that parent view requires guardian_token. This is clear usage context but no explicit 'when not to use' or alternatives are named, so it does not fully meet the 'explicit when/when-not/alternatives' bar.

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