Server Quality Checklist

Tool Scores

• generate_meal_planA
  3.6/5.0
  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 behavioral disclosure burden. It does reveal important output details (meal items, daily totals, achievement rates), but it omits any mention of side effects, data persistence, or authorization requirements. There is no contradiction, but the disclosure is only partial.

  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 communicates the main purpose, output, and intended audience without any filler. Every phrase carries meaningful information, making it highly concise and well-structured.

  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?

  Since an output schema exists, the description does not need to enumerate return fields, but it does mention them briefly. However, with 8 parameters and no guidance on how they interrelate or when to set them, the description is only partially complete. It captures the core scenario but leaves parameter handling unexplained.

  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 description coverage is 0%, and the description does not describe any of the 8 parameters. It only loosely alludes to goals via 'PRNT' and to duration via 'multi-day', which does not compensate for the missing parameter semantics. For a tool with 5 required numeric targets and several optional fields, this is inadequate.

  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 a multi-day meal plan according to PRNT goals, including 3 meals plus snacks, and specifies the output components (meal details, daily summary, achievement rate). This distinguishes it from the sibling tool get_meal_plan_nutrients, which suggests retrieval rather than generation.

  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 phrase '营养师调用' indicates the intended user (nutritionists), but there is no explicit guidance on when to use this tool versus alternatives. It implies usage for meal plan generation but lacks exclusions, conditions, or comparisons with get_meal_plan_nutrients.

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

• get_meal_plan_nutrientsA
  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 describes a read-only recomputation ('重新汇总') and validation intent, which implies no side effects, but it does not disclose potential error handling, behavior on malformed plans, or whether any data is persisted. The basic behavior is clear but not deeply detailed.

  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 in Chinese that front-loads the action and purpose with no filler or redundant information. Every word contributes meaning.

  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 tool's simplicity (one parameter, output schema provided) and the sibling context, the description covers the essential purpose, input, and validation intent. The output schema handles return format, so the description doesn't need to explain it. Minor gaps remain around edge cases, but overall it is sufficiently complete for this tool.

  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 has one 'plan' parameter with zero description coverage. The description compensates by identifying the parameter as the generated plan, but it does not explain the required structure or constraints beyond the schema's object type. Since the plan is likely complex and well-known from the sibling tool, this partial clarification is adequate but not comprehensive.

  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 re-aggregates overall average daily nutrients from an already-generated plan for validation purposes. The verb '重新汇总' (re-aggregate) and resource 'plan' are specific, and the mention of '已生成 plan' (already-generated plan) distinguishes it from the sibling tool generate_meal_plan.

  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 indicates the tool is meant for use after a plan has been generated, with the explicit intent of validation. This implies when to use it (post-generation) as opposed to generating a new plan, but it does not explicitly state when not to use it or list alternative tools.

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