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

Annotations already flag readOnlyHint=false and destructiveHint=false, and the description explains why: each call consumes one token, creates an XBOSS job, stores the processing result, and is explicitly "not purely read-only" even though it queries the institution's source. Idempotency behavior (generate a key before the first request, reuse it only for lost-response recovery, new key for a new execution) is also disclosed. Some residual vagueness in "기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다" keeps it from a 5.

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 is correctly front-loaded, but the body runs long and alternates between Korean and English in a way that splits the same idea across sentences. Phrases such as "anonymous taste calls" read like template residue and do not earn their place. The XBOSS-job sentence is a fourth restatement of the same non-read-only point.

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?

There is no output schema, so the description carries the burden of explaining what comes back; it gives counts (70 items, nine sections) but not the shape or structure of the returned form data. For a tool whose entire purpose is to hand back a large form definition, that is a real gap. The cost and side-effect information is otherwise adequate.

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% and both parameters are already documented, so the baseline is 3. The description adds real meaning: account_link_id must match the login account, and the idempotency key's lifecycle and its distinction from a provider-specific idempotency_key are spelled out. The schema itself defers to the description ("see the tool description"), so this added context matters.

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 names a specific verb-and-resource pair: it fetches the 70 input fields of the qualification-acquisition report plus the lists for nine sections (subject, four insurances, dependents). It also rules out what it does not do ("신고서를 만들거나 보내지는 않습니다"), which separates it from report-creating siblings. It never names the sibling tools it complements (e.g. draft_validate, or the change/loss variants), so it stops short of 5.

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 prerequisite is stated unambiguously in the first line: a prior nhis_edi__session__login call with the same account_link_id. The exclusion ("does not create or send the report") tells the agent this is a form-setup step rather than a submission step. However, it gives no explicit routing to which sibling should follow it in the workflow.

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