verify_citations

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety is covered. The description adds genuinely new behavioral context: it states the tool is 읽기 전용, that statute checking requires LAW_OC, and that '확인' means existence only (not content match). The one gap is that it doesn't warn about unverified/failed lookups beyond naming the 결과 values.

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?

Front-loads the English purpose statement, then uses compact labeled sections (언제 / 반환) so an agent can scan quickly. The enumerated return keys are dense but each carries meaning; there is little waste.

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 correctly takes on the burden of describing the return shape (문서번호/조문/요약/주의) and the caveat about existence vs. content. Auth prerequisite (LAW_OC) and the existence-only semantic are covered, leaving little an agent needs that is missing.

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 description coverage is 100%, so the schema already documents text, lang and as_of fully. The description adds no syntax or format detail for these parameters, so the baseline 3 applies; its detail is spent on return values rather than inputs.

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 verb and resource: 'Check that cited rulings, decisions and statute articles actually exist.' It also explicitly scopes itself against content-matching siblings, noting that '확인'은 존재만 뜻함 and that content verification belongs to get_tax_ruling·law_article. An agent can distinguish it from verify_statement and law_article without opening a schema.

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?

Gives an explicit trigger ('언제: AI나 사람이 쓴 초안을 내보내기 전') and the goal it serves (filtering fabricated document numbers and non-existent articles). It also names the alternative tools for the adjacent task of content matching, so the when/when-not boundary is clear.

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