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

The description adds genuinely non-annotated information: a cost of 20P per successful request, which matters for deciding whether to call it. Beyond that it says nothing about what the call actually does to state, what is returned (suggested text vs. a saved document), or how failures affect points. The "제안받습니다" framing sits in mild tension with readOnlyHint=false, though the per-request charge plausibly explains the non-read-only marking, so this is not a hard contradiction.

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?

Two short sentences, front-loaded with capability and then cost, with no padding. The cost is needlessly stated twice ("20P" in prose and the trailing "[20P]"), which is the only waste.

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 five-parameter, nested-object, multi-mode AI tool with no output schema, the description should say what comes back (suggested draft text? a modified document?) and when to prefer it over document_update or form_ai_fill. Neither is covered, and the point-consumption failure behavior is unstated, so an agent cannot predict the result of a paid call.

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 text, action, document, selection, and request_id, making 3 the baseline. The description reinforces the action/selection semantics (초안, 양식 채우기, 선택 문장 수정) but omits summarize/expand from its list and adds nothing about the 3,000-character limit or the nested document object.

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?

"에이픽에이전트로 문서 초안·양식 채우기·선택 문장 수정을 제안받습니다" states a concrete verb (receive AI suggestions) and three concrete resources that map onto the draft/fill/polish actions. It is clear what the tool produces, but it never distinguishes itself from siblings such as document_update or form_ai_fill, and the mismatch between the name "write" and the verb "제안받습니다" (receive proposals) leaves mild doubt about whether anything is persisted.

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?

No when-to-use, when-not-to-use, or alternative routing is given, despite obvious overlap with document_create, document_update, and form_ai_fill in the sibling list. The agent must infer from the tool name alone whether to call this or the plain CRUD document tools.

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