Server Quality Checklist

Tool Scores

• classify_ckdA
  4.4/5.0
  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 of disclosure. It reveals that the tool requires specific inputs, returns a structured output, and is restricted to physicians (an auth-related trait). It does not explicitly state that it is read-only or how it handles invalid inputs, but the computational nature is implied and the description adds context beyond the raw schema.

  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 compact and front-loaded. It uses three short sentences to convey purpose, input requirements, and output. Every sentence contributes 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 classification tool with an output schema, the description is quite complete. It covers the primary purpose, inputs, output summary, and a clinical reference (KDIGO 2024). Minor gaps include handling of cases where both uacr and upcr are provided or invalid eGFR values, but these are not critical given the tool's straightforward nature.

  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 0%, but the description compensates by explaining that eGFR is required and that uacr and upcr are two alternative measures of albuminuria ('albuminuria choose one'). This gives meaningful context to the parameters, though it does not provide units or acceptable value ranges (which are partially evident from parameter names).

  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: performing KDIGO 2024 pediatric CKD combined staging. It specifies the required input (eGFR) and optional albuminuria measures, and lists the return values (G/A stage, combined stage, explanation, follow-up intensity). This distinguishes it from the sibling tool calc_egfr_schwartz, which calculates eGFR, by focusing on staging.

  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 input prerequisites ('eGFR required; choose one of uacr or upcr') and a restriction ('physician only'). This indicates when the tool can be used and by whom. However, it does not explicitly mention alternatives or when to use this tool instead of the sibling, so it stops short of full comparative guidance.

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

• calc_egfr_schwartzA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden and does disclose key behavior: formulas used, output units (ml/min/1.73m²), required BUN input for one method, and an under-2-years warning. It does not explain error handling or edge-case behavior (e.g., missing BUN, invalid method), which prevents a perfect score.

  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 compact, front-loaded with the core purpose, and uses bulleted method variants that are easy to scan. Every sentence adds information, and there is no redundant or filler content.

  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 is largely complete for a calculation tool: it covers methods, inputs, outputs, and a special warning. Since an output schema exists, return value details need not be fully described. However, it omits the intended age population (Schwartz is pediatric) and does not specify behavior when required inputs for selected methods are missing, so a small gap remains.

  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?

  Schema description coverage is 0%, but the description compensates exceptionally well: it explains all three method values, indicates bun_mg_dl is only needed for revised2009, and explains k_value as either age-based or an override. The formulas mention height and Sr (serum creatinine), and age_years is tied to age bands and the under-2 warning, so every parameter receives meaningful context.

  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 begins with a specific action and resource: '估算肾小球滤过率（Schwartz 系列）' (estimate GFR, Schwartz series) and adds the exclusivity restriction '医生独占'. This clearly distinguishes it from the sibling tool classify_ckd, which likely addresses staging rather than calculation.

  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?

  It provides clear usage context: doctor-only access, method variants with the KDIGO default, and the dependency on bun_mg_dl for revised2009. However, it does not explicitly state when NOT to use this tool or directly compare it with classify_ckd, so it falls short of fully explicit when/when-not guidance.

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