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

Annotations only say readOnlyHint=false; the description goes well beyond that by explaining why: a token is consumed per call, an XBOSS job is created and its result stored, and some programmes persist a draft on screen transitions with the outcome exposed via safety.save_executed. It also gives non-trivial idempotency-key semantics (reuse only to recover a lost response, new key for new executions) and notes the key is unavailable to anonymous calls.

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 body alternates between Korean and English boilerplate and carries generic filler ('기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다') that adds no tool-specific information. The idempotency paragraph is useful but disproportionate to a single optional parameter.

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 8-parameter search tool with no output schema, the description covers the essentials an agent needs: auth prerequisite, absence of submission, side-effect disclosure, and how to detect saved drafts. It leaves the return shape beyond 'a list of insured persons' undetailed, which is a minor gap given the full schema coverage.

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 every parameter with its own description, which sets the baseline at 3. The description adds a little meaning (no resident registration number is supplied because candidates are selected, not created) and expands the idempotency key the schema defers to it for, but it doesn't clarify query/paging behavior beyond the schema.

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 concrete verb and resource: it returns the list of employment-insurance insured persons at the workplace who can be designated as subsidy targets. It also clarifies that candidates are picked from this list rather than created, which separates it from the creation-family siblings, but it never names target_init or target_save explicitly, so the differentiation stays implicit.

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 front-loads a hard prerequisite (a prior work24__auth__npki_session__login call with the same account_link_id) and states boundaries ('제출은 하지 않습니다', no RRN required). It does not spell out when to call this versus target_init/target_save or what to do with pagination, so guidance is clear but not exhaustive.

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