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

Annotations already flag this as a non-read-only, destructive operation, so the mutation profile is covered. The description adds value beyond that: it discloses an internal validation pass before persisting, and a concrete rejection rule (two rows with identical income type + name + identifier are rejected), plus the optional-row short-circuit. It does not describe what is overwritten on a re-save or whether the operation is idempotent, which keeps it below 5.

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 critical precondition is front-loaded in caps, and the following Korean sentences each carry a distinct rule (where it saves, validation, optional rows, rejection case) with no filler. The mixed-language presentation is slightly awkward but does not cost an agent comprehension.

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 destructive save step in a multi-step filing flow with full schema coverage and no output schema, the description supplies exactly the missing operational context: auth precondition, validation behavior, optionality of the payload, and the failure condition. Nothing an agent needs in order to call it correctly 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 description coverage is 100%, so the schema already documents dclr_id, statement_rows, and account_link_id in detail, including the row fields and the multi-certificate caveat for account_link_id. The description adds only the optionality of statement_rows. With schema doing the heavy lifting, baseline 3 is appropriate.

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) and resource (per-payee statement rows for the local-income special withholding filing), and the title reinforces the resource. An agent can tell it apart from the generic 'submit' tool because it explicitly says it validates 인별 statement rows then saves. It stops short of naming which sibling (e.g. adjustment_save, target_save) it complements, so it is clear but not fully differentiated.

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 opening sentence gives a hard precondition (prior wetax__session__login with the same account_link_id), and the description states the statement is optional and that sending no rows advances to the next step. That is real usage context, not just a restatement of the name. However it never contrasts itself against the other *_save siblings, so there is no exclusion or alternative guidance.

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