Skip to main content
Glama

review_chapter

Review a novel chapter against quality gates and format rules, returning pass/fail status, a specific issue list, and elapsed time.

Instructions

【质检层·第一层】每章过程评审(100% 每章必过):L1 形态红线(fatal 毫秒级短路)→ L2 打分 → AI 味 + TTS 格式 + 章名 + 暗爽点 + 单章自洽弱信号 + 节奏信号。输出 通过/打回 + 具体问题清单 + 真实耗时。

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": {
      "project_id": "<project_id>",
      "chapter_no": "<chapter_no>",
      "text": "<text>"
    },
    "name": "review_chapter"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes章节正文
factsNo事实契约 {rules:[{name,must_not:[正则],must:[正则?]}]},确定性校验
titleNo章名(若已有章纲可省略)
chapter_noYes
project_idYes项目 ID(内部代号,如“默者”)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden; it does disclose the internal pipeline (L1 fatal short-circuit → L2 scoring) and the return contents (通过/打回 + 问题清单 + 真实耗时). That is useful process transparency, but it omits whether the tool is read-only or persists issues/state, and what triggers the 'fatal 毫秒级短路' vs full scoring path.

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 dense, front-loaded sentence using 【质检层·第一层】 and arrows to convey layer and stage order efficiently; nothing is wasted. Slightly jargon-heavy with no whitespace, but structurally sound and immediately scannable.

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

Completeness4/5

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

Given 5 params, a nested facts object, no output schema and no annotations, the description is fairly complete: it spells out the output shape and the staged pipeline. It is only short on state/side-effect disclosure and prerequisites, which for a review gate would help an agent invoke it correctly.

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 80% and the description adds no per-parameter detail beyond what the schema already documents (project_id, chapter_no, text, title, facts). With coverage that high the schema does the heavy lifting, so the baseline of 3 is appropriate.

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?

States a specific verb+resource (每章过程评审 / per-chapter process review) and enumerates the exact checks it runs (红线, AI味, TTS格式, 章名, 暗爽点, 自洽, 节奏). This clearly distinguishes it from the granular sibling checks (check_redline, check_ai_flavor, check_format) as the composite gate. It loses a point for never explicitly saying it aggregates/replaces those individual check_* tools.

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

Usage Guidelines4/5

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

Strong mandatory-usage signal: '每章过程评审(100% 每章必过)' tells the agent this must run on every chapter, which is clear when-to-use context. However it does not say when NOT to use it, nor does it name the check_* siblings it subsumes or state prerequisites (e.g. whether the chapter draft must exist first).

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