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

Annotations already declare non-read-only, idempotent, non-destructive, and closed-world. The description adds genuinely new behavior: point-based cost (20P per write, 20P per attachment file), a point cap enforced per call, and that execution is asynchronous with results fetched later by job ID. It does not say what the start call itself returns, but the cost and async model are meaningful additions.

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 pricing sentence is duplicated verbatim, once plain and once in brackets ('견적 승인 후 작성 20P · 첨부 대조 파일당 20P' appearing twice), which is pure waste. The remaining sentences are short and front-loaded, but the repetition and the analysis/writing wording conflict hurt clarity.

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 9-parameter asynchronous workflow starter with no output schema, the description covers the essentials an agent needs: cost model, point ceiling, quote-approval precondition, and that the result is fetched later by job ID. What remains missing (the exact returned job ID field, which sibling fetches it) is minor.

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 all nine parameters including max_points, request_id deduplication, and total_max_points inheritance. The description only adds pricing context, not parameter meaning, so the 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?

The description says it accepts a document job within a point limit ('문서 분석 작업을 접수합니다'), which is a verb+resource, but the title says '작성 시작' (start writing) while the body says '분석' (analysis), leaving the actual operation ambiguous. Among many document_* and document_workflow_* siblings, an agent cannot confidently tell this apart from document_workflow_quote or document_workflow_apply.

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?

'견적 승인 후' (after quote approval) implies a precondition and ordering relative to document_workflow_quote, which is useful. But it never names the alternatives or states when not to use this versus document_ai_write or document_assist, and '작업 ID로 결과를 조회합니다' does not name document_workflow_get as the retrieval tool.

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