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

Annotations already declare readOnlyHint=false and openWorldHint=true, and the description corroborates this by stating the call is not purely read-only and creates an XBOSS task while storing results. It also adds a real cost signal ('호출마다 토큰 1소진'), which is useful beyond the annotations. However, the auth story is internally muddled ('no credential or login required' followed by 'for an authenticated call'), and the 'anonymous taste calls' line is garbled, reducing trust in the disclosure.

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 description is a mixed English/Korean block dominated by idempotency-key mechanics and generic compliance language ('기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다'). The actual purpose sentence is buried, and phrases like 'anonymous taste calls' read as artifacts rather than information.

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 mutating, open-world creation tool with five parameters and no output schema, the description leaves major gaps: the meanings of the two required IDs, what a 'case' contains on return, and how requested_submission_profile_ref affects creation. It does disclose side effects and token cost, which keeps it above the floor, but it is not complete enough for reliable invocation.

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 40%, so the description must compensate but does not: company_id and establishment_id are required yet never explained, and requested_submission_profile_ref is not mentioned at all. Only the idempotency key gets prose, and that prose is largely boilerplate also reflected in the schema field description.

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 Korean sentence '한 회사와 신고 기간에 대한 부가세 준비 사건을 생성합니다' states a specific verb (create) and resource (VAT preparation case) scoped to a company and filing period, so an agent can tell what it does. It does not distinguish itself from siblings such as vat__analysis__run, but the core purpose is unambiguous once extracted from the surrounding boilerplate.

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 description gives detailed instructions for when to reuse request_idempotency_key, but nothing about when to call this tool versus related tools like vat__analysis__run or the hometax VAT drafting tools. The 'period omitted selects the most recent closed period' note is buried in the schema rather than the description, and there is no guidance on preconditions beyond the ambiguous 'no credential or login required' line.

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