Retry failed, cancelled, or missing chapters in a terminal batch, recheck local text, merge consecutive positions, and return a new batch ID plus retry reference without touching successful groups.
仅重试指定终态批次中失败/取消分组仍缺失的章节；重新核对本地正文并按当前目录合并连续位置，返回新batch_id和retry_of。不会重试成功分组。
| Name | Required | Description | Default |
|---|---|---|---|
| batch_id | Yes | 必填，必须与当前批次一致，防止操作错批次 |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations only declare the generic non-read-only / non-idempotent / open-world profile; the description adds the operation-specific behavior: it re-checks local content, merges contiguous positions against the current catalog, and produces a brand-new batch rather than mutating the old one. That last point is valuable given idempotentHint=false, though it does not say what happens when no chapters qualify or whether the old batch is left untouched.
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 dense sentences with no filler, and the qualifying scope comes before the exclusion and return-value note. The phrasing is compact to the point of being terse, but every clause carries information.
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 single-parameter, non-idempotent operation with no output schema, the description covers the precondition, the exact subset acted upon, and the returned identifiers. The only real gap is the edge case where no chapters are missing and how errors surface.
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 the batch_id field already documents that it must match the current batch to avoid operating on the wrong one. The description adds only the qualifier that the batch must be in a terminal state, which the schema does not carry. Baseline 3 is appropriate when the schema does the heavy lifting.
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: retry only the chapters still missing in the failed/cancelled groups of a given batch. It also scopes the result ('返回新batch_id和retry_of') and states a negative ('不会重试成功分组'), so the agent can distinguish this from the download-starting siblings without opening any schema.
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?
It gives a clear precondition (the batch must be in a terminal state) and an explicit exclusion (successful groups are never retried), which is enough to select this over tnd_start_download or a new batch. It does not name an alternative tool or say what to do if nothing is actually missing, so it stops short of full when/when-not routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.