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

Adds context the annotations do not: the authentication prerequisite, that the write targets a draft rather than a filed return, and a per-call token cost ('호출마다 토큰 1소진'). It does not flag the destructive behavior implied by destructiveHint=true (draft_mode=new wipes an existing draft), but the schema documents that, so no contradiction.

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?

Three short sentences with the prerequisite front-loaded and zero filler; each clause carries information. The mixed Korean/English cost sentence is compact but slightly less immediately parseable than the rest.

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 step in a multi-call report workflow with a nested payload and optimistic-concurrency parameters, the description covers the auth prerequisite and cost but omits the workflow position and what happens to prior draft data. The rich schema compensates partially, leaving this at minimum-viable-plus.

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 draft_id, draft_mode, expected_state_version, idempotency_key and account_link_id are already fully documented. The description only restates the account_link_id linkage; it adds nothing about the nested basic_document payload, so the baseline of 3 applies.

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 verb ('Save') plus the resource ('basic taxpayer/report information') and the target container ('a regular-withholding draft'), which is enough to separate it from init/preview/review/submit siblings. It stops short of explicitly contrasting with detail_save, which is the nearest neighbor.

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?

Gives one real precondition — a prior hometax__session__login with the same account_link_id — which is useful. It does not state where this step sits in the init → basic_save → detail_save → submit flow, nor when to prefer it over detail_save, so the ordering is left to inference.

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