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

Annotations already declare readOnlyHint=true / destructiveHint=false, so the safety bar is low, but the description adds genuinely non-obvious behavior: each call consumes one token ('호출마다 토큰 1소진'), the idempotency key is a client-side same-request recovery key that must be regenerated for a new execution, and it is unavailable for anonymous calls. It does not say whether init returns data or only establishes inquiry state.

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?

Prerequisite and purpose are front-loaded, and most sentences carry real information (idempotency lifecycle, token cost). The idempotency paragraph is slightly overlong and abstract—'Without it, calling again remains a new request' takes a re-read—but nothing is filler.

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?

Prerequisites, token cost, and idempotency semantics are covered, which is substantial for a stateful init call. However, there is no output schema, and the description never says what init yields or that purchases__page / purchases__result are the follow-on calls, so an agent still lacks the end-to-end picture.

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 coverage the baseline is 3, and the description earns above that for request_idempotency_key: it explains how to generate and persist it, the exact reuse condition (recover a request after a lost response), the consequence of omitting it, and that a provider-supplied idempotency_key is a different field not to be altered. Date-range and account_link_id meanings are left entirely 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 description gives a specific verb and resource ('Initialize KB Biz Card purchases inquiry for a date range'), which is far more than the title alone conveys. It does not, however, distinguish itself from its close siblings purchases__search / purchases__page / purchases__result, so an agent cannot tell from the text alone why it would pick init rather than search.

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 front-loads a hard prerequisite ('REQUIRES prior kb_biz_card__session__login call with same account_link_id') and spells out the conditional rule for reusing the idempotency key versus minting a new one. It stops short of naming the alternatives (purchases__search for a direct query, purchases__page for continuation), so the 'when not to use this' half is absent.

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