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

Adds substantial context beyond the annotations: it discloses that the operation files with the NTS, creates a receipt record (cvaId + rcatNo), has no cancel action, and costs one token per call. Annotations say destructiveHint=true; the description explains exactly what is destroyed/created and why it can't be undone.

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 login precondition and the IRREVERSIBLE warning before procedural steps. Every sentence carries weight; only the trailing token-cost note in Korean is slightly out of place in an otherwise English description.

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 9-parameter irreversible mutation with no output schema, the description covers the essential pieces an agent needs: auth precondition, irreversibility and its consequences, the two-step confirm protocol, and cost. Nothing critical is missing.

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 every parameter including confirm and the template enum with defaults. The description reinforces the confirm workflow but adds little the schema doesn't, so the 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 and resource: 'Apply for a certificate with an explicitly chosen template.' The 'explicitly chosen template' phrasing implicitly contrasts with the auto-template sibling, but no sibling (apply_auto, apply__national_tax_payment, etc.) is named, so differentiation is inferential rather than explicit.

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?

Clear preconditions: a prior hometax__session__login with the same account_link_id is required, and the confirm preview flow is spelled out ('call without confirm first ... then retry with confirm=true'). It lacks direct guidance on when to use this vs the specialized apply__* siblings, which is the one gap.

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