payroll.kr_severance_pay

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

Annotations already establish the safe, read-only, idempotent, closed-world profile, so the description is free to spend its words on behavior, and it does: the exact deduction sequence, the 12x conversion then division, progressive-rate application, pro-rating back by service-year ratio, and won-level rounding. It also discloses two edge behaviors an agent would otherwise get wrong — sub-one-year fractions round up to one year, and local income tax is excluded from the result.

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 front-loads the purpose and legal basis, then moves to computation, then to the two caveats, and every sentence carries information — nothing is filler. The mid-section enumerating the deduction steps is dense but justified for a tax formula where the method itself is the contract.

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 not be described, and the calculation method is well covered. But for a statutorily-versioned tax tool, the unexplained year, as_of, and include_proposed parameters matter — whether as_of pins a historical law version or include_proposed pulls in proposed amendments changes the answer, and the description is silent on all three.

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 0%, so the description must carry parameter meaning, and it does for three of six: severance_amount (퇴직급여총액), service_years (년 단위, 소수 허용, explicitly not months), and non_taxable (원 문자열). The remaining three — year, as_of, include_proposed — get no explanation at all, which is a notable gap given the schema supplies only bare titles.

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 names a specific verb and resource (퇴직소득세를 구한다) and anchors it to the governing statute (소득세법 제48조·제55조), which immediately separates it from sibling payroll tools like kr_salary and kr_year_end_tax_settlement. It also scopes what the result includes and excludes, leaving no ambiguity about what is being computed.

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?

Usage is implied rather than stated: the description tells you the inputs must be total severance pay, service years in years, and non-taxable amount, and warns you not to pass months, which is a genuine guard against a common misuse. However, it never says when to choose this over adjacent tools (e.g. tax.kr_pension_income or payroll.kr_gross_from_net), nor any precondition such as which year's rules apply.

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