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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that citations have passed law.go.kr verification, indicating reliability, and explicitly lists the output fields. It doesn't mention side effects, but as a search tool, read-only is implied. It could be more explicit about being non-mutating, but the detail provided is strong.

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 two sentences, both in Korean and English, and every phrase adds value. The first sentence establishes scope and data quality, the second covers usage and output. No filler, no repetition, and it's front-loaded with the core purpose.

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?

Despite no output schema, the description fully explains the return structure (회차, 과목, 문항번호, 공식 정답, 지문, 인용 조문/판례와 링크). It also covers the corpus size and verification. The parameters are all in the schema, and the description effectively complements them, making the tool's behavior predictable for an agent.

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 the schema documents the parameters. The description adds value by explaining that 'q' accepts docket numbers, statute articles, or keywords, and gives concrete examples ('2014도6992', '형법 제310조'). It also clarifies the output mapping, which enriches understanding beyond raw schema names.

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 verb 'search' and the resource 'Korean bar exam corpus', and details the scope (15 rounds, 2,340 questions) and what results include (round, subject, question number, official answer, text, cited statutes/cases, and links). This distinguishes it from siblings like lookup_precedent or lookup_statute by explicitly targeting the bar exam corpus.

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 provides clear context on what queries to use (e.g., docket number, statute article, keyword) and what it returns. It doesn't explicitly mention alternatives or when not to use this tool, but the specificity of the bar exam corpus makes the intended use case obvious. A slight deduction for not naming alternatives.

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