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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description adds materially: the exact miss payload with at most 5 `similar` candidates, the fact that a "-N" key suffix causes misses for ~12% of paragraphs, and that context truncation at part boundaries is not an error. These are behavioral traits an agent could not infer from the annotation set.

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 a one-line purpose, then clearly headed sections ([Purpose], [Usage], [Response], [Rules]) so an agent can scan to what it needs. It is on the long side with mild redundancy — the "quote content_text, never a snippet" rule echoes the Purpose section and the response field list — which keeps it from a 5.

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 2-parameter read tool with no output schema, the description supplies the response shape (standard, target, related_qnas, items[] with item_type semantics) and the error shape, which is exactly what would otherwise be missing. Nothing needed to call it correctly or interpret a failure is absent.

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 goes well beyond: unique_key must be passed verbatim with no normalization, may contain non-digit parts (B58, 6.1.1), and may need a "-N" suffix; context is scoped to one part and silently clamps at boundaries. Both parameters gain meaning not present in the schema's terse descriptions.

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 — returns the full text of a 기준서 paragraph together with surrounding context — and explicitly distinguishes it from the search tools ("a search snippet is never quotable evidence"). An agent can tell instantly that this is the retrieval-of-exact-text tool versus search_standards.

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 [Usage] section gives two concrete call patterns ("1116호 33문단 원문" → unique_key="1116-33"; "앞뒤로 더 넓게" → context=5) that map user intent to arguments. The [Rules] section adds when-to-retry guidance on a miss and how to route to get_qna via related_qnas, which is explicit when/when-not coverage.

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