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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral value beyond that: results are grouped by type, similar items are opt-in, and it imposes a citation-attribution obligation (source URL must be shown) with a copyright note — a constraint an agent must honor.

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?

A single dense paragraph that front-loads the returned groups, then the addressing rule, then the citation obligation. The copyright/citation sentences are long but functional; little is wasted, though the legal boilerplate could be trimmed.

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 carries the burden of describing return values and does so by enumerating the result groups by type. Combined with the input-specification rule and attribution requirement, an agent has enough to call it correctly; only edge behavior (no matches, group limits) is left to the schema.

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 coverage is 100% (baseline 3), but the description adds meaning the schema does not carry: it explains that the id comes from search/fetch results and that the std+para pair is an alternative addressing mode. That cross-tool linkage is genuinely useful parameter context.

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 names a specific verb (반환/return) and resource (연결된 자료/related materials), and enumerates the exact result groups (citing QnAs, audit cases, practice commentaries, basis paragraphs, topics, similar items). It is concrete enough to distinguish from siblings, though it never names an alternative tool explicitly.

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?

It states the precondition for invocation (you must have one paragraph/QnA/audit case/practice commentary as the anchor) and how to specify it via id or std+para, which implies usage. However, it gives no when-to-use vs alternatives guidance against search, fetch, or get_paragraphs, and no exclusions.

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