payroll.hourly_to_monthly_net

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

Annotations already cover safety (readOnly, idempotent, closed-world), so the description's value is in the algorithm: 209-hour default derived from 40h/week plus weekly holiday, floor to whole won before deductions, and deduction of the four major insurances plus 간이세액표 income tax. That is meaningful behavioral context beyond the annotations. It stops short of noting year-dependent rate versions or what include_proposed changes.

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?

Three dense sentences with the computation chain front-loaded and the parameter/override caveat last; little filler. The first sentence is long and clause-heavy, which slightly slows parsing, but no sentence is removable without losing real information.

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?

An output schema exists, so return values need no explanation, and the deduction pipeline is well covered. However, for an 8-parameter tool with zero schema descriptions, leaving the required 'year' and the optional 'as_of'/'include_proposed' unexplained leaves real gaps an agent must guess at when invoking it.

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 description coverage is 0%, so the description must carry the burden and it only partially does: it clarifies hourly_wage (KRW, string), monthly_hours (default 209, override for non-40h weeks), meal_allowance (비과세 한도), num_dependents, and children_8_20. Three parameters — the required 'year', 'as_of', and 'include_proposed' — are never mentioned, and string-vs-number formatting expectations are only implied.

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 precise verb and resource ('시급을 월 환산시간에 곱해 월급으로 바꾸고 ... 실수령액을 구한다') and makes the two-stage composition explicit, naming payroll.kr_salary as the sub-computation. An agent can immediately distinguish this from payroll.kr_salary (net from an already-known salary) and payroll.kr_weekly_holiday_pay without opening any schema.

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?

Gives a concrete selection rule for the main ambiguity: '주 40시간이 아닌 근로는 monthly_hours 를 직접 줘야 한다', telling the agent when the default 209 applies versus when to override. It never states the inverse case (if you already have monthly gross, use payroll.kr_salary instead), so routing guidance is clear but not exhaustive.

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