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

Annotations declare readOnlyHint=false, and the description substantiates why: it discloses that each call consumes one token, that an XBOSS task is created and the result persisted regardless of whether the provider record was retrieved, and that the call is "순수 읽기 전용이 아닙니다." This is genuine added context beyond the annotation, not a restatement. It does not quantify latency or describe what happens on partial failure of the stored task.

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 is padded: "Without it, calling again remains a new request" restates the preceding sentence, and "Keep any provider-specific idempotency_key unchanged; it is a different field" refers to a field that does not exist in this schema, which costs attention without paying it back. The Korean XBOSS/token sentences are informative but not integrated with the English text.

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?

Auth prerequisite, token cost, persistence side effect, and idempotency are all covered, which is substantial for a six-parameter tool. The gap is the outcome: with no output schema, the description never says what "select" yields (a worker identifier? a list of matches?) or how that result feeds the detail call, leaving the agent to discover the handoff empirically.

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. The description does add real meaning for request_idempotency_key beyond the schema's pointer (when to generate, when to reuse, that it is unavailable to anonymous calls) and links account_link_id to the login session. However, the required business parameters (insurance_year, worker_name, birth_ymd) and business_management_no receive no interpretive help in the description.

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 definition states a specific verb+resource: "Search and select a worker for COMWEL individual billed-premium inquiry." This distinguishes it from the sibling comwel__info__individual_billed_premium__detail, which presumably takes the already-selected worker. It stops short of naming that sibling explicitly, so the differentiation is inferential rather than stated.

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 actionable: a prior comwel__auth__npki_session__login call with the same account_link_id must exist. The idempotency key rules are spelled out in operational detail (generate before first request, reuse only to recover a lost response, new key per execution). What is missing is a stated condition for choosing this tool over the detail sibling or any when-not guidance.

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