can_eat

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

With no annotations, the description carries the full burden of behavioral disclosure. It thoroughly explains the tool's behavior: red/yellow card interception, returning need_more_info for incomplete input, reverse-calculating portion limits from daily budgets, providing green/yellow/red light conclusions, and applying amount_g restrictions. This goes beyond a basic summary and gives the agent a clear mental model of the tool's process.

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

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

The description is dense but every clause earns its place. It front-loads the trigger condition, then logically proceeds through interception, missing-info handling, complete-information calculation, and amount_g-specific guidance. No filler words, and the structure mirrors the tool's execution flow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 13 parameters, an output schema, and complex decision rules, the description gives a complete overview: it covers the rule-based interception, the need_more_info branch, the calculation methodology (potassium/phosphorus/sodium/protein budgets), the output conclusion format (traffic light), and the handling of optional amount_g. This is enough for an agent to invoke the tool correctly even in edge cases.

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

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

Although schema coverage is 100%, the description adds significant meaning beyond the field descriptions. It explains that ckd_stage, age_years, and weight_kg are triggers for need_more_info if missing, and that amount_g is used to provide a limit reminder. This connects the parameters to the tool's decision logic, which the schema alone does not convey.

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

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

The description opens with a specific trigger condition ('家长问「XX 能不能吃」时调用') and clearly states the tool's function: to evaluate whether a food is safe for a CKD patient, using red/yellow card rules, nutritional budgets, and portion calculations. This distinguishes it from sibling tools like find_substitutes or cooking_tips, which have different purposes.

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

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

The description explicitly says when to call (when a parent asks if a food can be eaten) and provides context for handling missing information (asking for CKD stage/age/weight). However, it does not explicitly mention when not to use the tool or name alternative sibling tools, so it lacks the full when/when-not/alternatives guidance.

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