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

Annotations declare readOnlyHint=false, and the description explains why: each call consumes one token, creates an XBOSS task, and is explicitly 'not purely read-only' despite being an inquiry. This resolves the apparent tension between '조회만 합니다' and the annotation, adding real context beyond the structured fields. It could still say more about what the XBOSS task persists, but the disclosure is strong.

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 front-loaded, which is good, but the body is long, bilingual, and the idempotency paragraph is verbose and repetitive. Several sentences could be tightened without losing meaning, so it is functional but not lean.

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?

With no output schema, the description carries the return-value burden and does so: it enumerates what the call returns (eligibility, workplace details, per-step values, blocked reasons). Combined with prerequisite and side-effect disclosure, an agent has enough to call it correctly, though the XBOSS side effect could be spelled out further.

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 meaningful idempotency-key semantics: generate before the first request, reuse only to recover a lost response, use a new key for a new execution, and keep provider-specific keys distinct. That is genuine value beyond the schema's field descriptions.

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 specific verb and resource: it initializes a local income tax special withholding report and returns eligibility, the workplace to report (masked reg number, name, jurisdiction code), per-step values, and blocked reasons. It also distinguishes itself from declarant_save, which is what actually creates the report. Clear enough to separate from siblings, though the mixed Korean/English phrasing slightly muddies the opening.

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 the prerequisite (prior wetax__session__login with the same account_link_id) and clarifies this is an inquiry/init step that does not create the report, naming declarant_save as the creator. It does not explicitly contrast against other siblings like review or target_save, so it stops short of full when/when-not guidance.

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