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

Beyond the annotations the description discloses two genuinely useful behaviors: the stored adjustment/payment/penalty figures are computed server-side from the input rather than echoing the values sent, and each request creates an XBOSS job whose result is persisted. It also correctly reinforces that the call is not pure read-only, matching readOnlyHint=false. It stops short of saying what existing saved data is replaced, which matters given destructiveHint=true.

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 and the server-computation note is valuable, but the closing sentence ("기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다") is boilerplate that carries no actionable information, and the read-only disclaimer largely restates what the annotations already declare. Mixed Korean/English and generic disclaimers dilute the signal.

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 stateful mutation tool with no output schema and 8 fully documented parameters, the description covers the auth prerequisite, the side effects (XBOSS job, server-side recomputation) and the ordering hint. What is missing is where this step sits in the broader declaration lifecycle and what happens to a previously saved adjustment.

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 100%, so the parameters are already fully documented and the baseline is 3. The description does add one meaningful caveat — that server-computed values may differ from the submitted amounts — but it does not explain how the optional refund/carryover/additional-payment fields feed that computation or what dclr_id ties to.

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 states a concrete verb and resource: save the tax amount and adjustment details to the institution ("기관에 저장합니다 ... 세액과 조정 내용을 저장합니다"). Combined with the title it is clear this is the adjustment/tax-amount save step. It never distinguishes itself from the many sibling save steps (declarant_save, statement_save, target_save), so an agent has to infer which save it needs from the name alone.

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 gives one hard prerequisite up front ("REQUIRES prior wetax__session__login call with same account_link_id") and implies workflow ordering by telling the agent to confirm totals before saving. There is no statement of when not to use it, no mention of a required prior init/declarant step returning dclr_id, and no reference to any alternative save tool in the same family.

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