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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond them: the authentication prerequisite, the idempotency-key recovery semantics, and the per-call token cost ('호출마다 토큰 1소진'). Those are useful operational facts, though the idempotency paragraph is convoluted and its exact effect is hard to parse.

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 essential requirement is front-loaded, which is good, but the middle is bloated with repetitive idempotency sentences ('Without it, calling again remains a new request') that could be one line. The trailing Korean token note feels appended rather than integrated.

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 and idempotency are covered, but for a tool with sibling __init/__page/__result tools and no output schema, the description never says whether search returns rows directly or whether a follow-up result call is needed, nor how max_pages/pagination behaves. That is a meaningful gap for calling it correctly.

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 baseline is 3, but the description genuinely adds meaning for request_idempotency_key — explaining when to reuse it (lost-response recovery) versus when to generate a new one, which the schema defers to the description. The other seven parameters get no added semantics in the description, relying entirely on 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?

States a specific verb and resource: 'Search KB Biz Card approvals rows.' That is clear enough for an agent to know what it does. However, it never distinguishes itself from the sibling paginated tools (approvals__init/__page/__result) or from payments__search/purchases__search, so an agent cannot tell from the description alone how the search relates to those flows.

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?

The opening sentence gives a hard precondition: 'REQUIRES prior kb_biz_card__session__login call with same account_link_id,' which is explicit when-to-use guidance. It does not, however, say when to choose this over the sibling approvals__page/__result tools, leaving the workflow relationship to inference.

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