Permanently deletes a published or draft chapter only after explicit confirm=true; use to remove unwanted chapters when irreversible deletion is intended.
删除章节（已发布/草稿均可，⚠️ 不可恢复）。必须显式传 confirm=true 才会真正执行。
| Name | Required | Description | Default |
|---|---|---|---|
| book_id | No | 可选，默认当前选中的书 | |
| confirm | Yes | 必须为 true 才会删除，防误删 | |
| item_id | Yes | 章节 item_id（从 list_chapters / list_drafts 取） |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and delivers the two most critical facts: the operation is irreversible (⚠️ 不可恢复) and a destructive side effect applies to both live and draft content. It omits secondary behavior such as whether a missing confirm errors out or silently no-ops, and any permission/login preconditions.
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, zero filler, with the destructive warning and the confirm gate front-loaded before any call is attempted. Every clause 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 destructive, 3-parameter tool with no annotations and no output schema, the description covers the essential facts an agent needs: irreversibility, applicable content states, and the confirm gate. Only the failure mode when confirm is absent or false is left unspecified.
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% and each parameter already documents itself, including the meaning of confirm and the source of item_id. The description's confirm sentence largely restates the schema, adding only emphasis on the guard rather than new syntax or edge-case behavior; 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?
States a specific verb and resource (删除章节) plus the scope it accepts (已发布/草稿均可), so the agent knows exactly which objects are in range. It does not name a sibling or explicitly contrast with publish_chapter / list_chapters, but no competing delete tool exists, so ambiguity is low.
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 scope clause implies when the tool applies (any chapter, published or draft), and the confirm requirement tells the agent the invocation precondition. There is no explicit when-not guidance, no note on retrieving item_id first, and no mention of alternatives for restructuring rather than deleting.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.