search_decisions

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral context beyond annotations, such as how to obtain full text via options and the integrated nature of the search. No contradictions. It appropriately complements the annotated safety profile.

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 moderately sized but front-loaded with the core purpose. Every sentence adds value: domain enumeration, usage hints for specific cases. While it could be slightly more compact (e.g., removing the repeated domain list already in schema), it remains well-structured and informative.

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?

With 6 parameters, a nested object, and no output schema, the description covers major behavioral aspects: which domains exist, how to activate full text, and a special case for NTS. It does not explain response format, but given the readOnly and idempotent annotations, the description is sufficiently complete for typical search usage.

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%, so every parameter has a description. The description goes further by illustrating concrete usage for domain and options (e.g., 'domain='precedent', options.includeText=true, options.detailLimit=N'), which adds practical meaning beyond the schema's generic descriptions. This extra guidance helps the agent form correct calls.

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 it is an integrated search across 18 specific domains, using a domain selector. It distinguishes itself from siblings like search_law or get_decision_text by emphasizing its multi-domain scope. The verb '통합 검색' (integrated search) and explicit domain list make purpose unmistakable.

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?

Provides specific guidance on when to use certain domains: domain='precedent' with options.includeText=true for full text, and domain='nts' for tax interpretations. It implicitly tells when not to use other siblings (e.g., get_decision_text for a single decision). Lacks explicit exclusions or alternatives among siblings, but sufficiently covers common use cases.

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