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

Annotations only say destructiveHint=true; the description goes far beyond by disclosing the concrete consequence chain — buyer is notified, the invoice enters VAT filing, correction requires a 수정세금계산서, and this service's modify tool can only issue a full-cancel version (reasons 04 and 06). It also discloses per-call cost ('호출마다 토큰 1소진') and the preview/confirm handshake, none of which annotations convey.

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?

Front-loaded with the hard prerequisite, then purpose, then irreversibility, then the confirm workflow, then cost — a deliberate ordering that matches the order an agent needs the information. Dense but zero filler; each sentence carries a distinct constraint.

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 12-parameter, irreversible mutation with no output schema, the description covers everything an agent needs before calling: auth prerequisite, irreversibility and its correction path, the confirm/preview protocol, what the preview does and does not contain, and the cost per invocation.

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 schema already documents all 12 parameters, including confirm's approval semantics, so the baseline of 3 applies. The description adds only marginal parameter-level value: the note that supply amount and tax are server-computed and absent from the preview, while the remaining business fields (splr_tin, account_link_id, bill_method, etc.) are covered entirely by the schema.

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 and resource ('Issue an e-tax invoice') plus the destination agency (국세청), which is unambiguous against the sibling read tools (search_list/detail/statistics) and against hometax__etax__invoice__modify, which it explicitly contrasts.

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 an explicit prerequisite ('REQUIRES prior hometax__session__login call with same account_link_id'), an explicit two-step protocol (call without confirm for a preview, get user approval, retry with confirm=true), and an explicit prohibition ('Never set confirm=true on your own'). It also names the corrective alternative and its limitation, so the agent knows exactly when this tool is and is not the right choice.

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