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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses three useful traits: the login prerequisite, per-call token cost ("호출마다 토큰 1소진"), and detailed idempotency-key semantics (reuse only to recover a lost response, new key for a new execution). Deductions for the confusing line about "anonymous taste calls" and the ambiguous provider-specific idempotency_key warning, which muddy rather than clarify behavior.

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 the middle of the description is a dense, repetitive idempotency paragraph (three separate sentences restating key reuse) that crowds out pagination guidance. The "anonymous taste calls" sentence is noise an agent cannot act on.

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?

For a read-only paginated fetch with full schema coverage and safety annotations, the description covers prerequisites, cost, and idempotency adequately. It does not say how an agent knows it has reached the last page or whether search_context expires between calls, which matters for a paging 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, but the description adds real value here because the schema explicitly defers to it for request_idempotency_key semantics and defines the reuse-vs-new-key rule that the schema field cannot express. It still says nothing about page semantics (bounds, termination) beyond the schema's "Page number to fetch."

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 ("Fetch one KB Biz Card purchases page") and scopes it to a prior search context, which sets it apart from init/search. However, it never names or distinguishes it from the closely related siblings purchases__result and purchases__search, so an agent must infer the boundaries.

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 stated explicitly and unambiguously: "REQUIRES prior kb_biz_card__session__login call with same account_link_id," plus the dependency on a prior search context. What's missing is any exclusion or routing guidance (e.g., when to call purchases__result instead of another page), so the agent has context but no explicit alternatives.

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