record

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

No annotations are provided, so the description carries the full disclosure burden. It does reveal meaningful side effects (fatigue weighting, inventory rotation) and fuzzy matching, but it does not detail exactly what is modified, whether duplicate records are allowed, or how reversible the action is.

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?

One compact sentence packs the action, purpose, and matching behavior with no filler. The action pattern is front-loaded, making it immediately scannable for an agent.

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 one-parameter tool with an output schema and low complexity, the description covers the essentials for selection and invocation. It could add a pointer to undo_record for accidental entries, but nothing critical is missing.

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?

The input schema only lists 'name' with no description, and schema coverage is 0%. The description compensates by identifying the parameter as a tea name and noting that fuzzy matching is supported, which adds meaning beyond the schema. It omits format or matching details, but with only one parameter the core meaning is clear.

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 uses a concrete pattern ('我刚喝了XX') to define the tool as recording a tea-drinking event, and clearly states the downstream purpose (fatigue downweighting and inventory rotation). It is distinguishable from siblings like add_tea and undo_record despite not explicitly naming them.

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 implies the trigger condition (the user has just drunk a tea) and gives clear context for when the tool is relevant. However, it does not explicitly say when not to use it or point to alternatives such as undo_record for correcting mistakes.

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