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

Substantially exceeds the annotations: it discloses the auth prerequisite, per-call token consumption ("호출마다 토큰 1소진"), and full idempotency-key lifecycle (recover-a-lost-response vs. new execution) plus a caveat to leave provider-specific keys untouched. What it does not resolve is the tension with readOnlyHint=true — the repeated-execution and idempotency framing implies a stateful call, which the description never clarifies.

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 auth requirement is front-loaded well, but the single core action statement is buried mid-paragraph under three sentences of idempotency mechanics, and the trailing Korean token-cost note dangles at the end. Not wasteful overall, but poorly ordered.

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 9 optional parameters and no required fields, the description should explain which parameters actually identify a notice (row_key vs. row_index vs. template_code vs. notice_year_month) and whether they are alternatives or a combination. It covers auth and idempotency well but leaves the selection inputs entirely to the schema.

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 extra point by fully explaining request_idempotency_key semantics that the schema explicitly defers to it for. It still says nothing about how row_key, row_index, and template_code relate to one another when selecting a row.

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 the verb and resource ("Select a specific pension premium notice"), so the domain object is identifiable. However, "select" is never disambiguated — it could mean retrieving detail, marking a row server-side, or initiating a downstream process — and the sibling nps_edi__b1__pension_notices__search is never mentioned to contrast the two.

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 gives a concrete precondition ("REQUIRES prior nps_edi__auth__npki_session__login call with same account_link_id"), which is real routing value. But it never says when to pick this over pension_notices__search or pension_notification_documents__detail, so the agent must infer the workflow position.

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