verify_citations

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely non-structured context: article checks require LAW_OC, '확인' means existence only (not content match), and result codes distinguish 국세청 DB 미확인 from 조회 실패. Missing only operational details like rate limits or cost.

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-loaded one-line purpose followed by labeled 언제/반환/주의 blocks. Every sentence earns its place: purpose, trigger, return shape, and the existence-vs-content caveat. No filler.

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?

No output schema exists, so the description compensates by sketching the return object (문서번호 array with 인용/결과/제목/일자/링크/비슷한 번호, 조문 array, 요약, 주의). Combined with the auth note and semantic caveat, an agent has everything needed to call and interpret this tool.

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 all three parameters (text, lang, as_of) are already documented in the schema, including the 20,000-character limit and the YYYYMMDD format. The description adds nothing parameter-specific, so the baseline 3 applies.

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 (verify/check) and resource (cited rulings, decisions, statute articles), and explicitly carves out what it does NOT do: content matching is deferred to get_tax_ruling and law_article. An agent can distinguish this from every sibling without opening the 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?

The '언제' line gives an explicit trigger (before exporting AI- or human-written drafts) and the goal (filter out fabricated document numbers and nonexistent articles). It also names the alternative tools for the adjacent task of content verification, so the routing boundary is unambiguous.

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