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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description adds real context beyond that: the calculation standard used (AAHA/AAFP), the years+months summing rule, and the instruction to cite webUrl as the source.

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?

Front-loads purpose, then requirement, then examples, then output-citation guidance; every element is useful. The Korean/English pairing duplicates content, which costs a little tightness but keeps it usable for mixed-locale agents.

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?

With annotations covering the safety profile and an output schema present, the description does not need to enumerate return fields. It still covers inputs, standard, and the webUrl citation, leaving only minor gaps (e.g., units/cap on the human-year conversion output).

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?

Schema coverage is 100%, so baseline is 3, but the description adds the key cross-parameter constraint that the schema does not encode (required is empty, yet at least one of years/months is needed, and providing both sums them). That is genuine semantics beyond the schema.

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?

States a specific verb+resource: converting a cat's age into human years and returning a life stage (자묘·청년·성묘·노령, per AAHA/AAFP). This is unmistakably distinct from siblings like estimate_cat_food, get_cat_profile, or list_cat_breeds.

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?

Tells the agent the input precondition (at least one of years or months, summed if both) and gives concrete invocation examples. It does not name alternatives or say when not to use it, but the sibling set is far enough apart that ambiguity is low.

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