correction_compare

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

With no annotations provided, the description bears the full burden of behavioral transparency. It tells the agent this is a read-only comparison view of pre/post correction time series, which implies non-destructive behavior. However, it doesn't disclose details like pagination behavior, result ordering, timezone handling, or whether it returns both series merged or separate. For a read-only lookup tool, this is acceptable but not rich.

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 description is one concise sentence in Korean that states what the tool does and its purpose. It is appropriately short and front-loaded with the action. It could optionally mention parameter constraints, but for a lookup tool with a 100% schema coverage, this length is appropriate.

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 tool of this complexity (4 params, no output schema, no nested objects), the description conveys the core purpose and use case but doesn't clarify what the output structure looks like. Without an output schema, a note about the result format (e.g., columns, how before/after series are represented) would improve completeness. Sibling tools like correction_trend and correction_devices exist, but the description doesn't explain how this tool differs from them in terms of output.

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%, meaning all four parameters (deviceId, startDate, endDate, maxRows) already have descriptions in the schema. The description adds the contextual meaning that these parameters define the time series comparison (before/after correction), but doesn't add format or syntax details beyond what the schema provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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 ('조회한다' - retrieves/looks up) and resource ('보정 전/후 시간별 시계열' - time series before/after correction), and explicitly mentions its purpose ('보정 효과 검증에 쓴다' - used for correction effect verification). This provides a clear distinction from general data lookup tools like data_search or data_raw_search, though it doesn't name a sibling explicitly.

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 phrase '보정 효과 검증에 쓴다' (used for correction effect verification) gives clear context on when to use this tool. While it doesn't explicitly state when NOT to use it or name alternatives, the purpose statement is specific enough to guide an agent toward this tool for correction comparison scenarios and away from general data retrieval tools.

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