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

blind_review

Reinject independent blind judgments into a complete three-stage novel review pipeline, validate and audit results, and clear caches before and after to prevent cross-review contamination.

Instructions

P2c:用独立盲评 judgements 回注完整三审流水线,附校验与命中审计;前后清缓存防污染。

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>",
      "judgements": "<judgements>"
    },
    "name": "blind_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
factsNo
personaNo
chaptersYes
platformNoqimao
judgementsYes
clear_cacheNo
revised_idsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.4/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden. It does disclose useful side effects — validation, 'hit' auditing, and cache clearing before and after to prevent contamination — but it never states whether the tool writes or mutates pipeline state, whether re-injection overwrites prior review results, or what happens on validation failure, which are critical for a 7-parameter reinjection tool.

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

Conciseness3/5

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

It is a single compact sentence with no filler, and the core action is front-loaded. However, the leading 'P2c:' code and compressed terms like '命中审计' consume space without adding usable meaning for an outside agent, so terseness comes at the cost of clarity.

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?

This is a complex tool: seven parameters, nested objects, required chapter and judgement payloads, side-effecting cache behavior, no annotations, and no output schema. Against that complexity, one sentence covering only the action and cache clearing leaves the majority of invocation-relevant information — input shapes, return behavior, failure modes — unstated.

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?

Schema description coverage is 0% across seven parameters, including a nested object ('judgements') and an undocumented 'revised_ids' filter. The description only gestures at judgements and cache clearing; chapters, facts, persona, platform, and revised_ids get no meaning at all, so an agent must guess their formats and roles.

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

Purpose3/5

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

The description names a specific action (回注/fold blind-review judgements back into a three-review pipeline) and mentions validation and audit, so the general shape is visible. But it is written in dense internal jargon and an opaque phase code ('P2c:'), and it never distinguishes itself from close siblings such as blind_review_package, blind_compare, or blind_validate_judgements, whose names suggest overlapping validation work.

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?

There is no explicit when-to-use or when-not-to-use guidance and no named alternative. The 'P2c' phase prefix hints at a pipeline stage, but an agent cannot infer from the text whether to call this instead of blind_validate_judgements or blind_review_package, nor what preconditions (prior blind review output) are required.

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