tax.kr_withholding_simple

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

Annotations already cover read-only/idempotent/closed-world, and the description adds real substance: the tax amount excludes the 10% local income tax, sub-1000 KRW is truncated to select the [inclusive, exclusive) row, the >10,000천원 formula path, the >11 dependents rule, and the child 8-20 deduction. It says nothing about how `year`, `as_of`, or `include_proposed` affect which table or rules are applied, which is a meaningful gap for a tax calculation.

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?

Dense but front-loaded: the tool's purpose and calculation method come first, followed by parameter semantics and exclusions. Every sentence carries information, though the parameter notes could be grouped more tightly rather than interleaved with the calculation rules.

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 explained, and the calculation method is well covered. However, with 0% schema description coverage and three parameters (year, as_of, include_proposed) undocumented anywhere, an agent cannot determine what `as_of` or `include_proposed` mean — a real ambiguity for a versioned tax table.

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 carries the burden. It gives strong semantics for monthly_salary (KRW Decimal string, excludes non-taxable pay and tuition), dependents (includes the taxpayer), and children_8_20 (the 8-20 age deduction), but leaves year, as_of, and include_proposed entirely unexplained.

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+method: computes monthly wage withholding tax using the Enforcement Decree's simplified tax table (별표 2 간이세액표). This is clearly distinguishable from siblings like payroll.kr_year_end_tax_settlement or payroll.kr_salary, and the computational basis is named explicitly.

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?

Explicitly excludes the annual settlement case ("연간 정산(연말정산)에는 쓰지 않는다"), which routes the agent away from this tool for year-end work. It does not name the alternative tool directly, so the agent must infer that kr_year_end_tax_settlement handles that case.

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