check_originalityChecks manuscript originality locally, comparing n-gram similarity with your library and flagging self-repetition, filler density, dialogue share, paragraph balance, and daily word-count.
本地原创性检测：与文稿库其它条目做 n-gram 相似度比对，同时检查自我复读、套话密度、对话占比、段落均匀度、字数是否达日更门槛。不联网、不消耗额度。用 article_id 或直接传 content。
| Name | Required | Description | Default |
|---|---|---|---|
| content | No | 待检测正文（与 article_id 二选一） | |
| threshold | No | 相似度阈值，默认 0.25，越低越严格 | |
| article_id | No | 本地文稿 article_id（与 content 二选一） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses that detection is local with no network access and no quota consumption, and lists the specific analyses performed. It stops short of describing the result shape or what the similarity/threshold verdicts mean in practice.
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?
Purpose is front-loaded and the sentence is dense without filler; the offline/no-quota clause earns its place by reassuring the agent about cost. Slightly long with several comma-separated checks, but no wasted sentences.
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?
No output schema and no annotations exist, so the description should ideally convey what the tool returns (scores, flags, verdicts). It fully describes inputs and the checks performed but leaves the return format unspecified, which is the main remaining gap for an analysis tool.
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 three parameters including the 二选一 constraint between content and article_id, which the description merely restates. It adds no syntax or format detail for threshold beyond what the schema provides, so 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+resource (本地原创性检测) and enumerates exactly what is checked: n-gram similarity against the manuscript library, self-repetition, cliché density, dialogue ratio, paragraph uniformity, and word-count threshold. None of the sibling tools perform originality analysis, so the resource is 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?
It clarifies input selection — '用 article_id 或直接传 content' — and notes the operation is offline and quota-free, which tells the agent it is safe to run repeatedly. However, it gives no explicit when-to-use guidance (e.g. before publishing or saving) or workflow context relative to save_article/publish tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.