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

Beyond the readOnlyHint/destructiveHint annotations the description adds real behavioral facts: the auth dependency on a prior login with a matching account_link_id, the per-call cost ("호출마다 토큰 1소진"), and full idempotency-key lifecycle semantics including that omitting the key makes every call a new request. The one gap is that it never describes what the response contains, which matters because there is no output schema.

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?

The prerequisite is correctly front-loaded, but roughly four of the eight sentences are idempotency boilerplate that crowds out the actual purpose, and the trailing Korean cost note sits after the boilerplate. The core "what this returns" content is squeezed into a single clause while low-priority mechanics dominate.

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?

Auth, cost, and idempotency are all covered, which is more than most definitions do. But for a read-only lookup with no output schema, the description never says what business information comes back, and it does not differentiate itself from the adjacent client_info__get, leaving the agent unable to predict the result.

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 earns an upgrade by explaining the meaning of request_idempotency_key rather than restating it: generate-and-save before the first call, reuse only to recover a lost response with identical arguments, new key for a new execution, and a note that the provider-specific idempotency_key is a different field. account_link_id is only echoed ("same account_link_id") and relies on the schema's own detailed description.

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 specific verb and resource ("Get business info") scoped to e-tax invoice purposes, so an agent can tell roughly what it does. However, the near-identical sibling hometax__etax__client_info__get is never mentioned, and "business info" is not decomposed into the fields returned, so the boundary between the two lookups stays ambiguous.

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?

A hard prerequisite is spelled out ("REQUIRES prior hometax__session__login call with same account_link_id"), which is genuine usage guidance. But there is no when-to-use versus client_info__get, no statement of what this is needed for downstream, and no exclusions, so the alternative-selection signal is only implied.

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