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

Annotations already mark readOnlyHint=false and destructiveHint=true, but the description goes well beyond them by spelling out real-world consequences: buyer notification, automatic entry into VAT filing, irreversibility, and correction only via a 수정세금계산서. It also discloses the preview/confirm safety behavior and explicitly forbids setting confirm=true autonomously.

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?

Every sentence earns its place: prerequisite, core action, legal consequence, two-step confirmation workflow, and a blunt safety rule. The key constraints are front-loaded with REQUIRES and IRREVERSIBLE, and the whole description is compact for a destructive 12-parameter tool.

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 complex destructive tool with no output schema, the description still gives an agent everything needed to execute safely and correctly: when to call, what the first call returns (a preview), what to do with it, and how to confirm. The explicit preview/approval contract compensates for the lack of a documented return schema.

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?

With 100% schema description coverage, the schema carries most of the parameter load, but the description adds important cross-parameter meaning: confirm is tied to the preview-then-approve workflow, and account_link_id must match a prior login session. These relationships are not inferable from the individual parameter descriptions alone.

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 precise action — issue an e-tax invoice to 국세청 — and adds a key behavioral distinction from the modify/search siblings by noting an issued invoice can only be corrected via a 수정세금계산서. The resource and target are explicit, so an agent can immediately tell this apart from invoice search or modify tools.

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 an explicit prerequisite (prior hometax__session__login with the same account_link_id) and a precise two-step protocol: call without confirm first to get a preview, show the user, then retry with confirm=true only after approval. It stops short of explicitly naming sibling modify/search tools and stating when not to use this tool, but the required context is clear.

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