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

Annotations mark it read-only/idempotent, and the description goes well beyond them: it discloses the tool's boundary (does not adjudicate delay days), the disclaimer surfaced in counted_days, the warnings it emits (미선언·한도 적용·용어 비대칭), and the semantics of inferred=true (interpretation rather than statute text). These are exactly the subtle behavioral traits an agent needs before trusting the number.

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 critical rule (rate divergence by org_type) and uses bold headers to separate usage rules, boundary conditions, and response fields; the response-field list is justified because there is no output schema. It is nonetheless dense and occasionally restates enum values, so it is efficient but not maximally tight.

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, 4-required legal calculation tool with no output schema, the description supplies the full picture: when to use it, how to set each non-trivial enum, the computed pipeline (환산 → 한도 → warnings), and the meaning of every response field. Nothing an agent would need to invoke it correctly is missing.

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 description coverage is only 13% (only include_footnotes is documented in-schema), so the description carries the burden and does so thoroughly: it glosses the English enums in domain terms, and adds non-obvious rules such as '추측 금지' for org_type, the omit-vs-explicit-0 distinction for excluded_days and accepted_portion_amount, and the 연차별 계약금액 caveat for long-term contracts. This adds substantial meaning beyond the bare schema.

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 (지체상금/지연배상금 산정) with the exact decision logic applied (법정 요율·기준금액·30% 한도). It further distinguishes itself by spelling out that national vs local use different rates and legal terms, so an agent can tell it apart from sibling lookups without opening a 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?

Gives a clear when-not rule ('이 도구는 지체일수를 정하지 않는다') and routes the agent to search_references (and get_law_article for 원문) when exemption facts are disputed, plus an explicit instruction to confirm org_type with the user. It does not, however, route against close siblings such as delay_exemption_guide, so this falls short of a full when/when-not/alternatives matrix.

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