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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers substantial extra behavior on top: it refuses to invent a missing adjustment rate and returns 'met: null' plus why_null instead, suppresses single-item amounts when the base is absent, and declares which factors were NOT applied (등락폭 특칙·일반관리비·이윤 → computed.not_applied). It further discloses the non-obvious dual-track rule that a sub-3% rate can still yield single_item_only, which directly prevents a wrong '조정 불가' answer.

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?

The purpose and the 'what this cannot do' caveat are front-loaded before the long requirement list, which is the right ordering for a dense legal tool. It is long and occasionally repetitive — the verdict enumeration and the '그 자재에 한하여' distinction are restated — but nearly every sentence carries regulatory content an agent needs, so the length is largely earned.

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 a 14-parameter, read-only determination tool with no output schema and 7% schema coverage, the description closes the important gaps: it describes the response shape (verdict values, computed.track, why_null, footnotes) and enumerates the six deterministic checks that produce them. An agent can call this correctly and interpret the result without any other source.

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 7%, so the description has to carry the load, and it does: 12 of 14 parameters get targeted semantics in the Args block, including non-obvious rules such as org_type being unguessable because single-item thresholds differ, contract_date meaning the first contract date for long-term contracts, negative rates being passed through as-is for reductions, and single_item_base_amount being the item's own base amount rather than the whole-contract amount. Enum and default behavior (method_specified_in_contract defaulting to 품목조정률 with disclosure) is also spelled out.

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 ('물가변동 계약금액 조정 요건 판정 + 산식 적용') and pins it to a lifecycle phase ('이행단계 Phase 3'), making the domain unambiguous. It never names a sibling tool to contrast with, so an agent must infer where the boundary with get_law_article/search_law lies from the description alone.

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?

Concrete trigger questions ('자재값이 올랐는데 계약금액을 올려받을 수 있나', '90일 지났나', '단품 조정 되나') tell the agent exactly when to reach for this tool. It also sets a hard scope exclusion ('이 도구는 조정률을 산정하지 못한다 — 이 서버는 그 데이터를 갖고 있지 않다'), but it never routes the agent to a named alternative tool for the rate data.

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