verify_citations

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

No annotations are provided, so the description carries the full burden. It discloses that the tool extracts all numbers, checks existence in KIPRIS, compares names, and checks whether rights are alive. It also mentions the KIPRIS call limit consideration in the max_citations parameter. It doesn't mention rate limits, failure behavior, or what happens when no citations are found, but the core behavioral traits are well covered.

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, front-loaded with the core action and outcome, then the use case. Every sentence earns its place. The Korean text is dense but not bloated.

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?

For a tool with 2 params, 100% schema coverage, and no output schema, the description covers the main behavioral aspects: what it verifies, how it works, and when to use it. It doesn't describe the return format, but with no output schema and a clear verification purpose, an agent can infer the result. The only gap is explicit failure/edge-case behavior (e.g., no citations found, invalid text).

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 both parameters. The description adds context: '통째로' (whole text) reinforces the text parameter's purpose, and the KIPRIS call limit rationale for max_citations adds meaning beyond the schema's default/range. This is above the baseline 3 because the description explains why the limit exists.

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 tool's purpose: it verifies whether patent numbers cited in text are real, checking existence in KIPRIS, name match, and whether the right is still alive. It also names the intended use case (LLM-generated technical documents, IR materials, patent analysis reports) and distinguishes it from siblings by focusing on whole-text verification.

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 explicitly says when to use this tool: when you have a full text with cited patent numbers and want to catch hallucinations. It doesn't explicitly say when not to use it or name alternatives, but the sibling context (rights_alive, search_ip) and the phrase '통째로 검증' imply this is for batch verification of a document rather than single-number lookup. A clear exclusion statement would push this to 5.

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