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

impact_plan

Generate a zero-cost impact plan for revised novel chapters, showing which need full re-review, summary-only review, or cache reuse without calling an LLM.

Instructions

查看影响半径:哪些章全文重评、哪些只走摘要、哪些复用缓存。零成本,不调 LLM。

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": "impact_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
radiusNo
chaptersYes
revised_idsNo

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, the description must carry behavioral disclosure, and it does give one valuable trait: the operation is free and does not invoke the LLM. It omits whether it is read-only or mutates cache state, whether chapters must already exist, and what the returned plan looks like, so the safety profile remains unclear.

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?

Two short, front-loaded clauses: what it shows, then its cost profile. No filler, though the dense wording leaves key terms unexplained rather than being verbose.

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?

No output schema and no annotations, so the description alone must inform the agent, and it covers purpose and cost but not input meaning or result shape. For a three-parameter planning tool with a nested-ish chapters array, that is adequate but leaves real gaps.

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%, so all three parameters — radius, chapters, revised_ids — are undocumented beyond their titles. The description only implies that chapters and revised IDs drive classification, without explaining what radius does or how revised_ids differs from editing chapters, so it only partially compensates.

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 names a specific output concept: it classifies chapters into full re-review, summary-only, or cache reuse — a concrete decision, not a restatement of the name. It is somewhat metaphorical ("影响半径") and never explains the underlying model, but an agent can still tell it produces an impact/scope breakdown rather than a review.

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?

It states a key usage fact — zero cost, no LLM call — which implies it should be run before expensive review tools like review_chapter or blind_review, but it never says so explicitly nor names any alternative. The conditions under which to call it versus those siblings are left to inference.

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