Skip to main content
Glama
獬豸(Xiezhi)小说投稿评审 MCP Server

獬豸(Xiezhi)小说投稿评审 MCP Server

by proteus-vue

extract_facts

Extracts hard data from novel chapters to generate candidate fact contracts compatible with fact_check, flagging cross-chapter same-unit multi-value suspects for review.

Instructions

从正文抽硬数据生成候选事实契约(fact_check 兼容)。零 LLM,候选需复核,含跨章同单位多值 suspect。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "chapters": "<chapters>"
    },
    "name": "extract_facts"
  }
}

Input Schema

NameRequiredDescriptionDefault
chaptersYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full load; it usefully discloses that extraction is deterministic ('零 LLM'), that output is non-authoritative and must be reviewed, and that it flags a specific cross-chapter same-unit multi-value 'suspect' case. It omits what '硬数据' actually covers, whether the call mutates anything, and how large an input it tolerates.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense sentence with the core action first, then constraints and edge cases. Every clause carries information; no filler, though the mixed parentheticals make it slightly cryptic on first read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations, yet the description never describes the shape of the 'candidate fact contract' it returns or how suspects are marked, which is exactly what an agent needs to consume the result. Combined with the undocumented 'chapters' structure, the definition is under-specified for a tool whose entire value is its structured output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single required parameter 'chapters' typed as an array of free-form objects at 0% schema description coverage, so the schema explains nothing. The phrase '从正文' weakly implies the array holds chapter text, but the expected element shape (fields like title/index/content) is entirely unspecified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource: extract hard numeric data (硬数据) from body text (正文) and produce candidate fact contracts, with an explicit compatibility target (fact_check). An agent knows what it produces, though it does not distinguish itself from checking siblings such as check_consistency or check_self_consistency.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It hints at a downstream pipeline via '(fact_check 兼容)' and '候选需复核', but never states when to call this versus the many check_* or review_* siblings, nor any preconditions on the input chapters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.