cancel_draftCancel an unpublished draft by marking it cancelled and logging an audit entry. Does not cancel published content, access RedNote, or delete history.
将未发布草稿标为 cancelled，并写入审计。不能取消已发布内容。不会访问小红书，也不会删除历史记录。
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | ||
| draftId | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true and readOnlyHint=false. The description adds valuable behavioral context: it writes an audit record, does not access Xiaohongshu, and does not delete historical records. This meaningfully clarifies the nature and side effects of the destructive operation beyond what the annotations convey.
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?
Three short sentences with no filler. The primary action is front-loaded, followed by the most important constraint and side-effect clarifications. Every sentence earns its place.
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For a simple two-parameter mutation with no output schema, the description covers the essential constraints (unpublished only), side effects (audit, no deletion), and external behavior (no Xiaohongshu access). Minor gaps such as idempotency or failure behavior are not critical given the tool's low complexity and protected safety annotations.
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 0%, so the description must compensate for undocumented parameters. It never explains that 'reason' is a required free-text justification or how it relates to the audit entry. Only draftId can be loosely inferred from the phrase 'unpublished draft', leaving reason's semantics entirely underexplained.
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 states a specific verb and resource: mark an unpublished draft as cancelled and write an audit entry. It also clearly differentiates itself from sibling operations by noting it cannot cancel published content and does not access Xiaohongshu or delete history, making its scope unambiguous.
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 description provides a clear boundary: only unpublished drafts can be cancelled, and published content is excluded. However, it does not explicitly name alternatives such as update_draft or approve_draft, nor does it give direct guidance on when to prefer this tool over them.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.