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

Annotations only declare readOnlyHint=false, idempotentHint=true, destructiveHint=false; the description adds the crucial non-obvious traits — billing occurs on the first result return, re-queries within the validity window are free, and results expire at resultExpiresAt. It does not explain why the call is flagged non-read-only beyond pricing, but that is a minor gap given how much cost/expiry behavior is disclosed.

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 action and state handling, then cost and expiry, which is the right priority order. The 14-item enumeration of result.* sections is long but substitutes for a missing output schema, so it mostly earns its space.

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?

With no output schema and a single param, the description fully carries the burden: it names the returned result sections (conditional on the products chosen at request time), the status/error codes to check, expiry behavior, and cost model. An agent has everything needed to call and interpret it.

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?

The schema already documents the single transactionId parameter at 100% coverage, but the description reinforces the provenance constraint (it must come from a req_hometax_biz_bundle response) and the reuse rule for polling, which matters for correct invocation.

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 (조회) plus the exact resource (사업자 국세 통합조회 결과) and pins the lookup key to the transactionId issued by req_hometax_biz_bundle, which cleanly separates it from the sibling request tool and from get_hometax_bundle (personal income tax).

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 state machine: AUTH_WAITING means wait for phone approval, COLLECTING means re-poll shortly with the same ID, RESULT_EXPIRED means a new authentication request is required. It also tells the agent which fields (resultAvailable, status, errorCode) to inspect before acting, leaving no ambiguity about when to poll vs. restart.

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