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

Annotations only declare readOnlyHint=false and idempotentHint=false; the description goes well beyond that by disclosing that a real phone notification is sent, that billing/charging occurs (20P on successful send), that the call returns transactionId and status, and that retrying during pending approval is harmful. This is exactly the side-effect and cost context the annotations cannot 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?

Purpose is front-loaded, followed by product/pricing semantics, the confirmation caution, the return-value-to-next-call flow, and the retry prohibition — each sentence carries distinct information. It is slightly cluttered by stating the charge twice (billing warning and the trailing [인증 발송 성공 시 20P] tag).

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 23-parameter, no-output-schema tool it covers the essentials: what it returns (transactionId, status), what happens on the user's phone, the cost, and the handoff to get_hometax_bundle. It does not explain that identity fields (name, birthDate, phone) must match the account owner or which optional certificate parameters are relevant per product, but the fully described schema fills most of that gap.

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 baseline is 3, but the description adds genuine meaning the schema lacks: products is a multi-select whose selection determines what actually runs, and the unit price is the sum of the selected products' prices. It does not clarify how the many certificate-specific optional parameters (year, format, delivery, *_open_yn) map to which products, leaving that to 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?

The first sentence gives a specific verb and resource (requesting simple self-authentication for personal national tax integrated lookup), and the description explicitly names the follow-up sibling get_hometax_bundle, so the agent can separate this 'auth request' step from the 'fetch results' step. It does not explain how it relates to the other req_* siblings, but the pattern is inferable.

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 states the precondition (get user confirmation first because a phone push and billing are triggered), the prohibition (do not repeat the auth request while approval is pending, do not auto-approve), and the exact next action (pass the returned transactionId to get_hometax_bundle). When-to-use, when-not-to-use, and the alternative step are all explicit.

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