전문 도구 찾기

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds the concrete payload ('도구 이름과 설명을 돌려준다') and the breadth of the index (80+), but leaves the matching behavior unexplained — whether it matches on tool names, descriptions, or both, and whether results are ranked.

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?

Two short sentences: identity and scope first, then return format. Dense but front-loaded with no filler. The category enumeration is long, though it doubles as usable query vocabulary, so it largely earns its space.

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 no output schema, the description does correctly state the return content, and the single parameter is fully covered. What's missing is the workflow contract for a meta tool — that discovered tools are then invoked via execute_tool, and whether results can be refined by re-querying with different intents.

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 an example-laden intent description, so the baseline is 3. The description earns an extra point by enumerating eleven concrete query categories (조세심판, 관세, 헌재, 행심, 공정위, 개인정보위, 노동위, 학칙, 조약, 영문법령, 용어) that work directly as intent values, materially beyond the schema's four examples.

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?

States a specific action (category search) over a specific resource set (80+ specialized tools: 조세심판·관세·헌재·행심·공정위·개인정보위·노동위·학칙·조약·영문법령·용어) and says what it returns (tool names and descriptions). The '[메타]' tag plus the category inventory makes it distinguishable from retrieval siblings like search_law or get_law_text, though it never names a sibling explicitly.

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 'meta / discovery' framing implies you call this when you don't already know the right specialized tool, and the schema examples clarify the query style. But there is no explicit when-to-use or when-not statement, and no mention of the natural follow-up (execute_tool), which is the key routing decision an agent faces in this 10-tool set.

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