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

With no annotations, the description carries the full burden and does reasonably well: it discloses the returned data set including source and 기준일 (base date), plus the side effect that an OilPicker link comes back with the result. It does not state error behavior for unknown or non-normalized regions, or how current the monthly rate is beyond the base date field.

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?

Three short sentences: what it returns, what it does not return, and what the agent should do instead. The most decision-relevant facts are front-loaded with zero padding.

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 one parameter, no annotations, and no output schema, the description usefully enumerates the return fields an agent would otherwise not know. It would be fully complete if it said what happens when the region is unknown or ambiguous (e.g., return an error vs. suggestions).

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% and the region parameter already documents naming conventions with concrete examples ('수원', '경기 수원시', '제주') and the province-level caveat. The description adds no additional meaning about the parameter, 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?

The description states a specific verb and resource in Korean and enumerates exactly what is returned: local currency type, this month's fuel discount rate, monthly limit, source, and base date. It also rules out per-station pricing. It does not name the sibling effective_fuel_price, which is the tool an agent might reasonably confuse it with given both are fuel-price-adjacent.

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?

'주유소별 가격은 주지 않습니다' explicitly states what this tool will not do, and the description instructs the agent to redirect price inquiries to the returned OilPicker link — that is a clear when-not and a handoff. The gap is that it never tells the agent to use list_regions to resolve a valid region name, nor contrasts with effective_fuel_price for actual pump prices.

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