Server Quality Checklist

Tool Scores

• upsert_food_diaryB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of disclosing behavioral traits. It does disclose that nutrients are caller-calculated via M5 and that caller scope is restricted. However, it doesn't clarify whether 'upsert' means update or append, nor how write_mode affects behavior, nor permissions or idempotency. Some useful context but incomplete for a mutation tool.

  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 sentence that front-loads the action and follows with a practical constraint. It is appropriately concise with no wasted words. However, domain jargon (MX-3, M5) may be cryptic, and the structure uses a parenthetical which slightly reduces scanability.

  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?

  The tool has 4 parameters, no annotations, and low schema coverage, yet the description does not explain write_mode behavior, entry structure, or error/conflict handling. An output schema exists but is not visible; still, the description leaves significant gaps about edge cases and how this tool fits into the larger workflow.

  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 does add meaning for 'caller' (restricting to parent_assistant/child_companion) and gives hints about 'entries' (nutrient content pre-filled by caller), but patient_id and write_mode are not mentioned. The description only partially compensates for the lack of schema 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 writes/appends food diary entries ('写入/追加饮食日记条目'), which is a specific verb+resource action. It also distinguishes from sibling tools like get_food_diary_summary and assess_pew_risk, which are read/analysis tools. The caller restriction adds context but doesn't confuse the core purpose.

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

  Usage Guidelines3/5

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

  The description implies usage for writing/adding diary entries and gives a clear caller constraint (only parent_assistant / child_companion), but does not explicitly state when to use this tool versus alternatives like get_food_diary_summary. There is no exclusionary guidance, so usage is implied rather than explicitly contrasted.

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

• assess_pew_riskA
  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 burden. It discloses the input/output behavior and return format, but does not mention side effects (though unlikely), handling of null albumin, or any algorithmic details beyond the output levels.

  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 front-loads the purpose and includes all essential information without waste.

  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 description covers the main required inputs and output, and the existence of an output schema covers return value details. However, it omits the optional albumin parameter and any nuance about the basis for risk levels, leaving a small gap.

  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 only broadly mentions '3-day averages and targets' without naming specific parameters or units. The optional albumin_g_L parameter is entirely omitted, leaving it unexplained.

  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 an independent PEW risk screening function, specifying the inputs (3-day averages and targets) and output (low/medium/high with rationale). It distinguishes itself from sibling tools by focusing specifically on PEW risk.

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

  Usage Guidelines4/5

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

  The description implies the use case: when PEW risk screening is needed based on 3-day averages vs targets. It provides clear context but does not explicitly mention alternatives or exclusions, such as when to prefer assess_intake_vs_target.

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

• get_food_diary_summaryA
  3.9/5.0
  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 clearly discloses a key behavioral trait: the operation is read-only and readable by all callers. This directly communicates safety and lack of side effects, which is valuable. However, it does not elaborate on aggregation behavior or potential edge cases beyond that.

  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 immediately conveys the action, resource, return, and read-only nature. Every word earns its place with no filler 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, and the presence of an output schema likely covers return value details. The description covers the read-only aspect and the aggregation purpose. It could be more complete by naming the parameters or hinting at aggregation logic, but given the simple nature and output schema, it is largely sufficient.

  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 by explaining the parameters. It only indirectly references the patient via '某患者' but does not explain 'caller' or provide any parameter-level detail. The schema itself only lists types without descriptions, leaving the agent with insufficient semantic guidance.

  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 a specific action ('读取并聚合' - read and aggregate) on a specific resource (a patient's food diary) and specifies the return value (diet_diary_3d). It also explicitly marks the tool as read-only, which distinguishes it from the sibling 'upsert_food_diary' that implies writing.

  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 its usage context (reading and aggregating a patient's food diary summary) but does not explicitly state when to use it over alternatives like 'assess_intake_vs_target' or 'calc_prnt_targets'. The read-only hint offers some guidance but no explicit exclusions or when-not-to-use scenarios.

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

• assess_intake_vs_targetA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It explains the computation purpose, required inputs, and optional adjustments, adding value beyond the schema. It does not disclose edge cases or explicit read-only behavior, but for a calculation/assessment tool, the behavior is sufficiently 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?

  The description is concise, with two sentences. The first sentence states the core purpose and outputs; the second adds key input requirements and options. No superfluous words, and it is well-structured for quick comprehension.

  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 (11 parameters, nested 'diet' object, output schema), the description is somewhat incomplete. It provides essential input hints and links to calc_prnt_targets, but it does not explain roles of most parameters or the interaction with sibling tools. The output schema likely covers return values, but parameter context is lacking, making it minimally viable rather than complete.

  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?

  The schema has 0% description coverage, so the description must compensate for parameter meaning. It explains the 'diet' subfields (avg_energy_kcal/avg_protein_g) and two optional parameters (is_edema, height_cm, pd_glucose_kcal_per_day) but leaves many required and optional parameters (e.g., age_years, sex, weight_kg, ckd_stage, dialysis_mode, growth_status, vegetarian_mode) unexplained, despite their importance in PRNT target assessment. The partial coverage is insufficient.

  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: '对照 PRNT 目标评估 3 日饮食日记均值' (assess 3-day diet diary mean against PRNT targets) and specifies outputs like energy/protein achievement rate, gap, and PEW risk. It uses a specific verb and resource, and the mention of '与 calc_prnt_targets 一致' distinguishes it from the sibling tool calc_prnt_targets.

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

  Usage Guidelines4/5

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

  The description implies usage when a 3-day diet diary with averaged values is available and PRNT targets are needed. It states required diet fields and lists optional adjustments (edema correction, PD glucose deduction), providing clear context. However, it does not explicitly exclude scenarios or mention alternatives like assess_pew_risk for detailed PEW assessment, so it lacks explicit when-to-use/alternatives.

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

• calc_prnt_targetsA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well: it discloses special behaviors like is_edema triggering ideal body weight correction and pd_glucose_kcal_per_day deducting energy targets. It also mentions Schofield cross-check for informational output. However, it stops short of explicitly stating that the tool is read-only or safe, though that is implied by 'calculate'.

  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 two sentences, with the main purpose in the first sentence and clinical details in the second. It is efficient but the second sentence is dense with technical terms, which is justified given the complexity. No wasted words, and it is front-loaded with the primary function.

  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 10 parameters, complex clinical logic, and an existing output schema, the description adequately covers the key special cases and adjustments. It does not explain the SDI methodology in depth or potential limitations, but the output schema removes the need to describe return values. The description is sufficiently complete for a calculation tool.

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

  Parameters5/5

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

  The input schema has 0% description coverage, so the description must compensate. It explains the key non-obvious parameters: is_edema ('启用水肿理想体重校正'), pd_glucose_kcal_per_day ('扣减膳食能量目标'), and refers to dialysis add-ons, vegetarian multiples, and growth status adjustments which map to other parameters. This significantly adds meaning beyond the raw 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's function: '按 PRNT 2020 计算儿童 CKD 每日能量与蛋白质目标' (calculate daily energy and protein targets for pediatric CKD using PRNT 2020). It specifies the method (age×sex segmented SDI) and adjustments, distinguishing it from siblings like assess_intake_vs_target and assess_pew_risk.

  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 through its purpose (calculating targets for children with CKD) but does not explicitly state when to use this tool versus alternatives. It mentions clinical features but lacks direct references to sibling tools or exclusions for cases where other tools would be more appropriate.

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