신고·경정청구·제척기간

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is added context — and it delivers the 5-year correction window and the weekend/fixed-holiday rollover rule, which is a real behavior the agent would otherwise miss. It does not state what the response contains, but that is the main remaining gap.

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?

Two dense sentences, zero filler, with the core purpose front-loaded before the holiday-rollover caveat. Nothing is wasted or buried.

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 8-parameter calculator with no output schema, the description enumerates the outputs conceptually but says nothing about the return shape — notably it never mentions the remaining-days figure that the `today` parameter and its '남은 일수' description imply. It also doesn't flag that non-fixed holidays (설·추석) must be supplied via extraHolidays; that only surfaces in the schema.

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 88%, so the schema already documents nearly every parameter including the periodEnd mapping per 세목 and the assessmentCase enum. The description only restates the kind/periodEnd framing and the 5-year constant, adding no format or interaction detail beyond the schema; baseline 3 applies.

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 (계산합니다) and enumerates the four concrete deadline resources it produces (법정신고기한, 경정청구 5년, 부과제척기간 만료일, 후발적 경정청구 기한), keyed on 세목 and 과세기간 종료일. That is enough to separate it from estimation siblings like estimate_tax/estimate_penalty, though no sibling 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?

The purpose implies when to call it (when a statutory date is needed), but there is no explicit when-to-use/when-not or routing to alternatives such as estimate_penalty or read_provision. The agent must infer the boundary between 'compute a deadline' and 'estimate an amount'.

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