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_compare

Compares original and blind review scores, decisions, and veto flags to surface discrepancies without altering the final judgment.

Instructions

事后对照原评审与盲评的分数/判定/否决差异;只呈现,不自动改写判定。

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": {
      "original_report": "<original_report>",
      "blind_report": "<blind_report>"
    },
    "name": "blind_compare"
  }
}

Input Schema

NameRequiredDescriptionDefault
blind_reportYes
original_reportYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden, and it does disclose the single most important trait: it only presents differences and never auto-rewrites the verdict, i.e. a non-mutating comparison. It says nothing about what the comparison output looks like (diff format, missing-field handling, whether scores are normalized) or any failure modes, which are real gaps for an unannotated tool.

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?

A single compact sentence that front-loads the comparison action and follows with the non-mutation constraint; no filler or repetition. Brevity is close to under-specification, but nothing in it is wasted.

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

Completeness3/5

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

There is no output schema, so the description must describe the return value, and '只呈现' leaves the shape of the presented differences undefined. Combined with two opaque nested-object inputs and no annotations, an agent knows what the tool is for but not precisely what it will get back or what inputs are required structurally.

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

Parameters3/5

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

Schema description coverage is 0% and both parameters are free-form nested objects with additionalProperties, so the schema conveys almost nothing. The description partially compensates by mapping 原评审/盲评 onto the two inputs and by enumerating the compared dimensions (分数/判定/否决), which hints at report contents. It still gives no structural expectation for the report objects or whether they must come from the same review cycle.

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 states a specific verb and two resources: it compares the original review against the blind review, and it names the compared facets (scores/verdicts/vetoes). That distinguishes it from siblings such as blind_review, which produce a review rather than diff it. It stops short of an explicit sibling callout, so it is clear but not maximally differentiating.

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

Usage Guidelines3/5

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

'事后' (after the fact) implies the timing condition: both reports must already exist. Beyond that implicit trigger there is no when-to-use/when-not guidance, no mention of which sibling produced the inputs, and no stated prerequisites. Usage is inferable but not spelled out.

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