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

Annotations already cover the safe-read profile (readOnlyHint, openWorldHint), and the description adds genuinely new cost behavior: 60 points per call and no charge when recall_target=false. It also repeats the mutual-exclusivity rule, which is already in the schema, and doesn't state what happens if neither identifier is supplied.

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?

Front-loaded with the purpose in English, followed by Korean detail on return values, billing, and parameter exclusivity. The bilingual restatement is somewhat redundant but each sentence carries either scope, cost, or input rules; nothing 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?

With no output schema, the description usefully previews the return shape: subject-or-not flag, recall count, per-recall content, and correction period. Combined with the billing rule this is nearly complete; it omits error behavior when both or neither identifiers are provided.

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% and the schema already documents both parameters, including formats ('차대번호 17자리', example plate numbers) and the 'do not send together' constraint. The description's parameter sentence duplicates the schema rather than adding format or validation detail, so baseline 3 applies.

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?

States a specific verb and resource — checking recall / free-repair campaign eligibility for a Korean vehicle — and names the two accepted identifiers (plate number or VIN). This is clearly distinguishable from the other vehicle_* siblings (emission, model info, tax, flooding, scrap), which cover different datasets.

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?

Explicitly constrains input: 'car_no 와 vin 은 둘 중 하나만 보냅니다' (send only one of the two). Also gives the non-recall pricing condition, which implicitly tells the agent when a call is free. It does not, however, contrast with alternatives such as vehicle_model_info or get_car_flooding, so there is no explicit when-not guidance.

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