공공데이터 조합 가능성 검사

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context by stating it does not call or combine raw data, reinforcing that it is a metadata-only check. This goes beyond the annotations by clarifying the tool's non-execution nature.

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 a single concise sentence that front-loads the primary action and adds a clarifying exclusion. Every clause contributes meaning without redundancy or fluff.

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?

The tool is simple (2 params, no output schema) and the description covers the core function and non-execution behavior. However, it lacks parameter semantics for 'regions' and provides no details about output or return values. It is minimally viable but has clear gaps for an agent's full understanding.

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 0%, so the description must explain parameters. It mentions '카탈로그 ID' (catalog ID) which maps to dataset_ids, but does not explain the 'regions' parameter or how it is used. The description only indirectly references 지역 (region) as a check item, leaving the regions parameter semantically unclear.

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 clearly states the tool checks whether selected catalog IDs exist and organizes items to verify on the official page (schema, region, auth, join keys). It uses a specific verb (확인, 정리) and distinct resource (catalog IDs). It also explicitly excludes calling or combining raw data, distinguishing it from sibling tools like recommend_data_combination or design_public_data_product.

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 description implies usage as a preliminary feasibility check before combining data, and notes it does not execute raw data calls or joins. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention cases where it should not be used. No alternatives or exclusions are named.

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