verify_pipa_citation

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

With no annotations provided (0% coverage), the description fully bears the burden of disclosing behavior. It details the stepwise verification process (4-tier check), special features (as_of temporal verification, alias normalization), and output markers ([HALLUCINATION_DETECTED]). It also mentions providing accurate evidence and next-tool guidance. This is comprehensive and transparent.

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 relatively short but dense with information. It is structured as a single coherent paragraph with clear logical flow (purpose, method, features, output, next steps). It avoids unnecessary words and front-loads the key points. Slightly more structure (e.g., bullet points) could improve readability, but it is already concise.

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?

Given the absence of an output schema, the description adequately explains what the tool does, how it works, and what it returns (hallucination markers, evidence, next-step suggestions). It also connects to sibling tools for follow-up actions. The complexity of verifying legal citations is well-covered, and the description leaves minimal gaps for a typical use case.

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?

Both parameters (citation and as_of) are described in the schema (100% coverage), and the description adds valuable context: examples of accepted citation formats for 'citation' (e.g., 'PIPA §15 ① 6호', '개인정보 보호법 제15조제1항제6호'), automatic alias normalization, and an explicit example for 'as_of' ('20190601'). This goes beyond the schema's basic constraints.

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 explicitly states the tool's purpose: to verify legal citations against an actual law API to detect hallucinations. It specifies the four-tier hierarchy (law, article, paragraph, subparagraph) and gives concrete examples like 'PIPA §15 ① 6호'. This clearly distinguishes it from sibling tools like search_law or get_law_text, which are for different purposes.

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 guidance on when to use the tool: to verify citations and detect hallucinations. It also includes next-step recommendations (search_law for full name, get_law_text for text), but does not explicitly state when not to use it compared to other tools like compare_articles or search_pipc_decisions. However, the context makes the intended usage fairly clear.

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