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

Annotations only give readOnlyHint=false, destructiveHint=false, openWorldHint=false; the description goes well beyond that by disclosing token cost per call, XBOSS job creation and result persistence, the 15-minute download URL and 7-day file retention, private recovery_receipt handling, and idempotency-key reuse rules. However, the lead line '조회만 합니다' reads as pure read-only and only much later is it corrected with '이 호출은 순수 읽기 전용이 아닙니다', which is a self-inflicted clarity problem the annotations do not resolve.

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 scope are front-loaded correctly, but a large block about anonymous results, private recovery_receipts, non-repairable loss by signing up, and signing in later has little bearing on a tool that explicitly requires an NPKI session. The XBOSS/token disclosure, which is the most important behavioural fact, is buried in the final paragraph, and the read-only framing contradicts itself across the text.

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 6-parameter tool with no output schema, the description supplies the return shape (per-programme eligible/ineligible/undetermined verdicts with undetermined excluded), the artifact channel, retention windows, and the recovery path for expired links. It omits what happens when the required login is missing or how programme keys are discovered, but nothing critical to a correct invocation is absent.

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, and the description surpasses it by explaining the semantics of request_idempotency_key (generate before the first request, reuse only to recover a lost response, new key for a new execution) and the artifact/link expiry behaviour tied to output_formats. programme_keys, application_year, business_management_no and account_link_id are already documented in the schema and get no extra treatment in the 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 core sentence is specific: '사업장 하나에 대해 고용24 사업주 사전진단을 실행하고 지원금 사업마다 판정(eligible, ineligible, undetermined)을 돌려줍니다' names the verb, the single-workplace scope, and the exact return values. It does not differentiate itself from the sibling 'subsidy_pack__diagnosis_v1__generate' or explain why two diagnosis entry points exist, 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?

The prerequisite is front-loaded and conditional ('REQUIRES prior work24__auth__npki_session__login call with same account_link_id'), and the description says what to omit to cover all programmes and what to do when a download link expires (call xdata__job__result with the job_id). It gives clear operating context but never states when NOT to use this versus other diagnosis/application siblings.

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