personal_deduction

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real substance beyond them: it declares the return fields (기본공제·추가공제·인적공제·사람별 내역·근거) and the underlying statutory rates (1인당 150만원, 경로우대 100만·장애인 200만·부녀자 50만·한부모 100만). It still omits eligibility thresholds and how conflicts are resolved, but nothing contradicts the 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?

Four terse lines with an explicit 언제/입력/결과 structure, front-loading the purpose before the input mapping and legal rates. Every sentence carries information; nothing is padding.

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 three required parameters, nested objects, no output schema, and a read-only safety profile, the description covers purpose, input mapping, result shape and rates — exactly what an agent needs to call it. It stops short of the age/income eligibility rules that materially affect which persons qualify, which keeps it from a 5.

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% and the schema itself is very rich (relation enums, income_items kinds, mutual-exclusion rule, examples), so the description's '입력:' line only restates year→귀속연도, taxpayer→납세자, persons→부양가족 목록. It adds labeling convenience but no semantics the schema does not already carry, matching the baseline-3 case.

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 the exact resource and its subcomponents (종합소득 인적공제: 기본공제·추가공제) and the '언제' clause supplies the verb by stating it computes the basic/additional deduction amounts in a comprehensive income tax return. This is enough to distinguish it from siblings like income_adjustment_total, special_tax_credit or income_tax, though it never explicitly contrasts itself with a neighboring tool.

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?

The '언제: 종합소득세 신고에서 기본공제·추가공제 금액을 구할 때' line gives a clear, concrete trigger condition for use. There is no when-not guidance and no named alternative for cases where the agent instead needs a credit, an income adjustment, or total tax, so the routing duty is only half done.

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