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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds materially beyond them: the shape of the returned bundle, a weak-evidence quality signal with a retry instruction, and licensing/citation obligations. These are behavioral traits an agent cannot infer from structured fields.

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 with the core purpose and content inventory, then usage, retry guidance, and citation rules in a logical order. It is a dense single block rather than a list, and the licensing sentence is long, but every sentence carries actionable information.

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?

There is no output schema, so the description must describe the return, and it does so concretely (standard paragraphs plus neighbors, Q&A/audit cases with cited paragraphs, practical commentary, source URLs, per-item ids). Combined with the retry and citation guidance, an agent has everything needed to call and follow up correctly.

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 std, domain, max_chars and question are already documented with examples and ranges. The description only adds that a natural-language sentence can be passed as-is, which slightly enriches the question parameter but does not compensate for anything since nothing is missing. 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 and resource ('회계위키의 근거를 한 번에 묶어 반환') and enumerates exactly what the bundle contains: standard paragraphs with surrounding context, related Q&A/audit cases, and practical commentary. It is clearly differentiated from siblings like fetch/get_paragraphs, which it explicitly names as the full-text follow-up.

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 when-to-use ('답변을 쓰기 전 근거 수집용'), tells the agent that a verbatim question is acceptable, and prescribes a concrete recovery path when the result carries the '근거 약함' warning (re-query with standard terminology). It also routes to the follow-up tools (fetch, get_paragraphs) via item ids.

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