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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description discloses the auth requirement, the reversible-while-작성중 window (which qualifies the destructiveHint), and a per-call token cost. These are genuine behavioral facts an agent cannot read off the annotations. It stops short of explaining what happens to previously selected targets when the save runs.

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?

Four short sentences with the hard prerequisite front-loaded, then the action, then the reversibility window, then cost. Nothing is redundant and no sentence is filler.

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 5-required-param mutation with full schema coverage and annotations present, the description covers auth, input provenance, reversibility, and cost. The remaining gap — whether the save replaces or appends to an existing target set, and what a successful response contains (no output schema) — is a real but modest omission.

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 description coverage is 100%, so every parameter is already documented in the schema, including where target_irnos comes from and where receipt_no originates. The description restates the target_search provenance already present in the schema and adds no new meaning for worker_type, labor_contract, or account_link_id — baseline 3 is correct.

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 a specific verb and resource — naming chosen 피보험자 as subsidy targets on a draft — and anchors the action to irno values from target_search. It implicitly separates itself from target_search (source of irnos) but does not explicitly distinguish itself from target_init or modify.

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?

Prerequisites are explicit: a prior work24__auth__npki_session__login with the same account_link_id, and target_irnos must come from target_search. It gives clear context for when this applies but does not name exclusions, e.g. when to use target_init instead of target_save.

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