tax.kr_inheritance

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, so the safety profile is covered. Beyond that, the description discloses the actual computation pipeline — deduction ordering, the 5억 lump-sum vs basic/personal deduction max, spouse deduction caps (legal share, 30억, 5억 floor), the 10~50% progressive brackets, the generation-skipping surcharge formula, and that the 3% filing credit is reported separately.

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-loaded with purpose, then the calculation order, with no filler sentences — each clause maps to a rule actually applied. It is a dense single block though, and the statutory citations plus parenthetical conditions make it harder to scan than it needs to be.

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 description gives enough of the tax logic to trust the result. However, for a 21-parameter tool with zero schema descriptions, several behaviorally important inputs (notably year, which drives the statutory version, and flags like include_proposed and spouse_sole_heir) are left unexplained, so an agent can still misuse 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?

With 0% schema description coverage the description must carry parameter meaning, and it does explain the money convention (원 단위 Decimal 문자열), gross_estate (과세가액 after pre-gift addition, denominator for the surcharge ratio), has_spouse, and implicitly use_lump_sum and timely_filing. But roughly half of the 21 parameters — year, as_of, decimals, rounding, include_proposed, spouse_sole_heir, spouse_legal_share_cap, renounced_inheritance, bequest_to_non_heirs, disabled_life_years_total — receive no explanation, leaving material gaps in a 21-param tool.

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?

Specific verb+resource: '한국 상속세를 계산한다' (calculates Korean inheritance tax), anchored to the statutory articles 제18조~제21조·제24조·제26조·제69조. It is unmistakably distinct from the sibling gift tax (tax.kr_gift) and income tax calculators without needing to open 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?

Usage is only implied by the tool name and the subject matter; there is no explicit 'use this when…'/ 'not for gift tax, use tax.kr_gift instead' routing. The one directive present ('배우자가 있으나 상속받지 않았으면 has_spouse=true 를 지정한다') is parameter guidance rather than when-to-use guidance.

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