Search an entire novel for semantically related passages using natural language queries, so you can find scenes by meaning even when exact keywords are unknown.
语义检索（本地 embedding，0 token）：自然语言检索全书语义相关段落，无关键词也能命中。
| Name | Required | Description | Default |
|---|---|---|---|
| top | No | 返回条数（默认 5，最大 10）。 | |
| book | Yes | 书名。 | |
| root | No | 章节库根目录（含 novels 子目录）。 | |
| query | Yes | 要检索的语义描述，如「与血统秘密相关的段落」「女主压抑克制的时刻」。自然语言越具体越好。 |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose useful behavior: local embedding (no external calls) and 0 token cost, which is genuinely valuable. However, it omits whether the operation is read-only, any scope limits (top max 10 is only in the schema), and pagination/traversal behavior across the book.
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?
A single tight sentence with no padding, and the most decision-relevant facts (local embedding, 0 token, works without keywords) are front-loaded. It is appropriately sized for the amount of information conveyed.
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 4-parameter search tool with no annotations, the description covers what it does and its cost profile but leaves gaps: no statement of return shape or result ordering, no mention that root configures the chapter library, and no routing guidance against the keyword-search sibling.
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 four parameters including the query examples and the top default/max. The description adds only the natural-language framing already implied by the query param description, so baseline 3 is correct.
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 (语义检索) and resource (全书语义相关段落), and the clause '无关键词也能命中' implicitly frames it as the semantic counterpart to keyword search. The closest sibling, novel_keywords, is never named, so the agent must infer the routing choice from the description's phrasing rather than an explicit contrast.
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?
Implied usage is clear: use natural language when you lack exact keywords. But there is no explicit when-not guidance and no named alternative, even though novel_keywords is the obvious competing tool. For 15 sibling tools, an agent benefits from being told directly when this beats keyword search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.