payroll.kr_donation_deduction

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

Annotations already declare readOnly/idempotent/openWorld=false, yet the description adds substantial domain behavior: 15%/30% bracket split with special-first ordering, political-fund 100/110 rule, 25% over-30M tier, and truncation below the won. It also discloses that certain donation types are excluded from amount calculation, which an agent cannot infer from annotations.

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 the computation goal and then layers the rate rules efficiently in four dense sentences with no filler. The tax jargon is heavy but each sentence carries operative rules an agent needs.

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 an 11-parameter, 0%-coverage tax tool with an output schema, the description captures the core calculation logic and exclusion rules well. Remaining gaps are the unmapped parameter names and undocumented auxiliary params (as_of, include_proposed, carryover_loss).

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 compensate. It clarifies earned_income as a won-denominated string and pins religious_donation's purpose, and maps several donation types conceptually — but it does not map special/general/hometown/ESOP terms to concrete parameter names, and leaves as_of, carryover_loss, include_proposed, and year 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 (구한다/computes) and resource (기부금 세액공제/donation tax credit) with statutory citations (소득세법 제59조의4제4항, 조세특례제한법 제76조). An agent can distinguish it from siblings like kr_medical_deduction or kr_education_deduction without opening the 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?

Clearly delimits scope: what gets computed (special/general and political donations), what only affects limit ordering (hometown/ESOP), and where religious donations must be routed (religious_donation). It does not explicitly name alternative sibling tools, but the calculation boundary is unambiguous.

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