공정위 공식 Q&A 검색

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

No annotations are provided, so the description carries the burden. It discloses that it works locally without an API key, that results include caveats, that older documents may contain abolished criteria, and that lit26-* items should be prioritized. It does not detail the return format, but for a search tool this is acceptable.

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 longer than average but well-structured with bolded text and bullets. The first paragraph establishes purpose and data source, while bullets add usage tips, warnings, and relationship to other tools. The specific count breakdown is slightly excessive but 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?

For a search tool with no output schema and no annotations, it provides a rich context: use case, query examples, category filter, warning about outdated content, preference for 2026 manual, and alternative tool for current standards. It lacks explicit result format details but covers the main operational 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 coverage is 100%, so baseline is 3. The description adds practical guidance: search queries work best with core nouns and provides three examples. It also explains category values in Korean and mentions that the query can be a natural sentence. This extra context elevates it above baseline.

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 searches official FTC Q&A from guides/FAQs/manuals, specifying the count and use case for edge cases. It distinguishes itself from check_disclosure_duty by noting that current numerical judgment is handled by that tool, and from other siblings by focusing on official Q&A.

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?

It explicitly says use when rules alone cannot determine boundary cases, gives query tips, mentions category filtering, and warns about outdated documents while directing to check_disclosure_duty for current numeric standards. It also notes that check_disclosure_duty's situation input searches the same knowledge base.

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