search_tax_interpretations

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

With NO annotations provided, the description carries the full burden, and it delivers: states exact scope (four types), explains match semantics (AND/OR/NOT), and discloses the data-sourcing tradeoff (direct NTS with fresh data, but not a legal mirror). Loses a point because it doesn't explain what fields are returned, pagination behavior beyond a 'page' parameter, or rate limits.

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 avoids filler, front-loads the core purpose in the first line with a period, and the remaining text efficiently covers types, filters, query semantics, and data-source advantage in sentence fragments. It's structured as a single dense paragraph that is readable.

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 complex, 13-parameter tool with no annotations and no defaults on half the fields, the description explains the semantics of match models (AND/OR/NOT), the exact-lookup path, and the source-freshness tradeoff. However, it doesn't describe the kind of data returned (e.g., fields/structures) since it relies on an output schema, which the rules allow. Minor gap: it does not explain default sort behavior or how to combine 'tax_type' and 'query'—two behaviors that would have completed the picture.

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?

The schema already has 100% coverage, giving a baseline of 3. The description adds value by clarifying that 'document_number' triggers exact lookup, and that whitespace-separated words become AND terms in the query parameter, which matches the 'query' parameter's description of quoted phrase behavior. However, it doesn't provide the full boolean logic detail for exclude or how sort values map to behavior—the description adds some contextual glue but doesn't fully compensate for what's missing in terse schema descriptions.

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?

Description states '국세청 세법해석례(예규)를 검색한다' with specific object (searching tax interpretations), lists the four categories covered, and differentiates itself from siblings by clarifying it directly queries the NTS original rather than the Ministry of Government Legislation mirror. It's specific and distinguishes the tool from search_tax_decisions, which handles rulings.

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 explains when to use this instead of the alternative by mentioning '법제처 미러가 아니라 국세청 원본을 직접 조회하므로 최신 예규가 바로 잡힌다'—differentiating from sibling tools that might query the other source. It also cites a data-freshness advantage over alternatives. Though it doesn't name sibling tools explicitly, it provides clear context for when this tool's characteristics matter.

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