search_tax_decisions

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the scope of search sources, that result filtering is supported, and prominently states that case_number triggers an exact lookup. It does not discuss pagination or result structure, but the presence of an output schema mitigates that need.

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 compact and front-loaded, with no filler or repetition of unrelated material. The dense list of target types/codes is necessary for scoping a search tool of this breadth and is immediately usable for an agent.

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?

Given the high parameter count and no annotations, the description explains the essential aspects: what data sources are searched, what document categories are covered, what filters exist, and how to use exact lookup. It does not discuss sibling-tool selection, but the tool name and description together with sibling names still provide sufficient context.

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 high (87%), so the baseline is 3. The description adds useful context beyond the schema by mapping the target types to their official category codes (05, 06, 07, etc.) and by emphasizing that case_number yields an exact lookup. It also ties decision result and attribution year to filter behavior.

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 uses an active verb ('검색한다') and clearly specifies the resource: tax case precedents and rulings from the National Tax Service, Tax Tribunal, and courts. It also lists the exact target categories and filter dimensions, making its purpose unambiguous and sufficiently distinct from sibling tools like search_tax_interpretations or search_tax_guidance.

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 gives clear context for when to use the tool: searching tax decisions/rulings, optionally filtering by decision result or attribution year. It explicitly tells the agent to use case_number for exact lookup when the case number is known, which is a strong usage guideline, though it does not name sibling tools or state when not to use it.

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