tax_research

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

No annotations are provided, so the description carries the full disclosure burden. It reveals key behavioral traits: the layer-by-layer evidence collection algorithm, the authorityLevel tagging mechanism for distinguishing legal effect, an explicit no-legal-conclusion guarantee (anti-hallucination), and the companion-tool suggestion. It falls short only on operational details like pagination, rate limits, or partial-failure behavior—minor gaps for a read-only research tool.

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 information-dense sentences with zero filler—the hierarchy, the authorityLevel mechanism, the scope caveat, and the companion-tool pointer are all load-bearing. The only deduction is structural: it's a heavy wall of text with no front-loading, bolded critical caveat aside, making it denser to parse than strictly necessary.

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 tool with 6 parameters and a multi-layer research model, the description covers the essential context: the layered pipeline, the distinction between statutes/interpretations/decisions, the authorityLevel mechanism, and the no-judgment behavioral guarantee. The output schema exists to document return values. Gaps like error handling and empty-layer behavior are minor for a research tool with an output schema.

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 coverage is 100% with well-described parameters (layered result counts for limit_per_layer, accuracy hints for tax_type), so the baseline is 3. The description's layer hierarchy does help interpret limit_per_layer and include_guidance (which map to specific layers like 기본통칙·집행기준), but it adds no parameter-specific detail beyond what the schema already provides.

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 a specific verb+resource: 'collects one tax issue as evidence' organized by an explicit hierarchical cascade (법률→시행령→...→판례·헌재). The layered research concept, authorityLevel tagging, and the explicit no-legal-conclusions scope clearly distinguish it from sibling search/lookup/get tools focused on individual document types.

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 names korean-law-mcp as an explicit companion tool for statutory text ('법령 본문이 필요하면'), gives an explicit scope exclusion for enforcement rules (시행규칙 '범위 밖, 확인 경로 안내'), and notes the tool's pure-research limitation ('법적 판단이나 결론을 만들지 않는다'). However, it never explicitly contrasts with sibling tools like search_tax_interpretations or search_tax_decisions, which an agent might confuse it with.

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