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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds real context beyond them: each call consumes one token, creates an XBOSS job and stores a result, so the call is 'not purely read-only' even though institution data is untouched. It also clarifies that no account numbers are returned and no payment is made. Slight tension between '조회만 합니다' and '순수 읽기 전용이 아닙니다' is resolved by the surrounding sentences, so it is not a contradiction, but the framing is muddled enough to fall short of 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 mixes Korean and English, repeats idempotency boilerplate that appears across tools, and contains a stray template artifact ('not available to anonymous taste calls'). Several sentences restate the same no-payment/no-account-number point, so the text is longer than the tool warrants.

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 three-parameter read tool with no output schema, the description covers authentication prerequisites, the returned data shape, token cost, side effects (XBOSS job creation), and idempotency recovery. The main gap is the absence of any guidance on interpreting a not-yet-paid status or what to do next, but nothing required to invoke the tool 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning for request_idempotency_key: generate and save it before the first request, reuse it only to recover a lost response with identical arguments, and use a new key for a new execution. That is behavior the schema's one-line description does not convey. dclr_id and account_link_id semantics are left entirely to the 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?

The description names a specific resource and output set: it returns whether a submitted filing has been paid, the number of payment virtual accounts, and the amount due ('제출한 신고의 납부 여부와 납부용 가상계좌 건수, 납부할 금액'). It also rules out two things explicitly (no account number returned, no payment performed). It does not directly contrast itself with siblings such as search_history or review, which keeps it from a 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?

It states a hard prerequisite ('REQUIRES prior wetax__session__login call with same account_link_id'), which is useful gating context. However, it never says when to choose this over sibling queries like special_withholding__search_history or when in the filing lifecycle to call it — usage is only implied by the mention of a previously submitted filing.

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