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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description adds real context beyond that: each call consumes one token (토큰 1소진), creates an XBOSS work item and stores the processing result. Its clarification that '기관 원본의 조회 여부와 별개로 이 호출은 순수 읽기 전용이 아닙니다' usefully reconciles the lookup behavior with readOnlyHint=false rather than contradicting it.

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 prerequisite and read-only caveat are front-loaded, but the text mixes Korean and English mid-block and repeats itself around idempotency ('Without it, calling again remains a new request'). The closing sentence about 기관 데이터 변경 following per-tool procedures is generic boilerplate that adds little.

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 mutation-free lookup with no output schema, the definition covers prerequisites, safety, and cost, but it never says what fields the returned 사업장 기본정보 contains. An agent can call it correctly but cannot tell whether the response answers its question.

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%, so the baseline is 3, but the description adds meaning the schema does not: account_link_id must match the account used for session login and only needs manual entry when multiple certificates are linked. It also carries the entire idempotency-key semantics (when to generate, when to reuse, anonymous calls excluded, provider idempotency_key is a different field) that the schema only gestures at.

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 states a specific verb and resource: it returns the workplace basic info held by the logged-in 건강보험 EDI session. It also scopes the tool by noting '사업장을 고르는 입력은 없고' (no input to select a workplace), which separates it from parameterized workplace lookups, though it never names a sibling such as nps_edi__b1__workplace__main_basic_info.

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?

It gives a hard prerequisite up front — 'REQUIRES prior nhis_edi__session__login call with same account_link_id' — plus the idempotency-key workflow (generate before the first request, reuse only to recover a lost response). What's missing is explicit when-not guidance or a named alternative for other-agency workplace data.

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