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

Beyond the annotations (readOnly=true, destructive=false), the description discloses the auth prerequisite and the per-call cost ('호출마다 토큰 1소진'), which are real behavioral facts the agent cannot get from structured fields. The idempotency-key section is unusually heavy for a read-only, zero-required-param call, and the 'anonymous taste calls' phrasing is unclear, but the substance is genuinely additive.

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-loading the login requirement is good, but five sentences are devoted to one optional recovery key on a read-only tool with no required parameters. The untranslated Korean token-cost note is buried at the end and easy to miss, while the idempotency prose dominates the reader's attention.

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 100% schema coverage, no output schema, and annotations carrying the safety profile, the remaining burden is auth/cost semantics — both covered. Nothing critical is missing, though a one-line note on what the selection returns (card identifiers usable downstream) would close the loop.

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 baseline is 3. The description earns an extra point because it is the canonical explanation of request_idempotency_key — the schema literally defers to it ('see the tool description') — and it clarifies when to generate, reuse, or replace the key. It does not add anything for account_link_id or the two department filters beyond what the schema already says.

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: 'Select KB Biz Card cards available to the current session.' An agent can tell this retrieves cards in the authenticated session. However, it never differentiates from the near-identical sibling kb_biz_card__common__departments__select, and 'select' alone leaves the read-vs-choose ambiguity until the readOnlyHint annotation resolves it.

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 prerequisite is explicit and front-loaded: 'REQUIRES prior kb_biz_card__session__login call with same account_link_id,' which is exactly the routing information an agent needs. It stops short of naming alternatives or stating when-not to call this versus departments__select or the approvals/payments tools.

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