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

With readOnlyHint=false already declared, the description adds real context: each call consumes one token, it creates an XBOSS task and stores the processing result, and it is explicitly 'not purely read-only' even when the institution side is only queried. It also discloses idempotency recovery semantics for lost responses. The remaining gap is that it never says what is written or whether re-invocation is safe without a key beyond 'calling again remains a new request.'

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 purpose sentence is buried after a prerequisite line, and the text drifts into generic boilerplate about token consumption, XBOSS tasks, and provider-specific idempotency_key fields. The untranslated Korean tail duplicates what the idempotency paragraph already conveys, adding length without new information.

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 an eight-parameter detail lookup with no output schema, the description covers the auth prerequisite, side effects, and cost, which is the important part. It still leaves the caller without a picture of what the detail response contains or how to disambiguate the several row-selection parameters, which the schema alone must carry.

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 schema already documents all eight parameters, which sets the baseline at 3. The description adds genuine value for request_idempotency_key (generate before the first request, reuse only for recovery, new key for a new execution), but says nothing about how row_key, row_index, goji_round, notice_year_month, and the *_text_contains filters relate to selecting one target.

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 second sentence states a specific verb and resource: 'Get health checkup target employee details.' That distinguishes it from sibling list/search tools such as nhis_edi__hr_payroll__health_premiums__employee_details and the premium-notice tools. However, the purpose statement is buried under a prerequisite sentence and does not explain what the 'detail' adds over the source list.

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 states a hard precondition ('REQUIRES prior nhis_edi__session__login call with same account_link_id') and key-reuse rules for request_idempotency_key. But it never says when to call this detail tool instead of a list or how row_key/row_index/goji_round/notice_year_month are used to select the target; the phrase about 'anonymous taste calls' is opaque and gives no usable guidance.

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