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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description adds real context beyond that: anonymous/no-login access, no institution connection, consumption of one token per call, creation of an XBOSS job and storage of results, and the explicit warning that this call is not purely read-only. This is genuine, hard-to-guess behavior, though it is delivered as dense boilerplate.

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 opening line and the "call this first" instruction are well front-loaded, but the body is bloated with conditional idempotency boilerplate that does not apply to this anonymous lookup call, plus a typo ("anonymous taste calls"). Korean and English are interleaved without a clear structure, so sentences compete for the reader's attention.

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 must explain what comes back. It says only that the tool reports required inputs and prep materials per step — no shape, no indication of whether steps are enumerated or how results should be fed into prepare/submit. For a low-complexity, zero-required-param tool this is adequate but leaves the handoff to the next step implicit.

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?

With one optional parameter and 100% schema coverage, the baseline is 3. The description earns above baseline by explaining the idempotency key's lifecycle — generate before the first authenticated request, reuse only to recover a lost response, new key for a new execution, and that provider-specific idempotency_key is a different field. The schema itself only points back to 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?

States a specific resource (원천세 신고 삭제신청 requirements) and a specific output — the inputs and prep materials needed per step. It also distinguishes itself from sibling steps by positioning itself as the first call. The Korean title and mixed-language body add noise, but an agent can tell what it does.

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?

"다른 단계보다 먼저 부르세요" gives explicit ordering relative to the prepare/submit siblings, and "No credential or login required" sets a precondition. It stops short of naming alternatives like candidates or prepare as exclusions, so exclusion guidance is missing.

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