Skip to main content
Glama

novel_sentence_config

Query or modify plugin, feature, and analysis switches for novel-writing workflows, including tool toggles, prompt modes, and auto-analysis settings.

Instructions

读写插件与分析开关配置(get 查询 / set 修改)。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "novel_sentence_config"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolsNo工具开关({novel_*:bool})
actionNo操作
enabledNo总开关
featuresNo功能开关(emotionCaveat/genreTheme/emotionComplexity/semanticEmbedding/semanticSearch/semanticStyle/semanticImplicit/rawWriting/webnovelVibe/lexiconFirst/chatWriting);rawWriting仅明确要求时开。
autoAnalyzeNo自动分析
promptSceneNofull档场景
leanWorkflowNo精简工作流(省token)
chatThresholdNo聊天提问字数阈值(100~5000,0=默认)
styleToleranceNo容差;空对象 {} 表示清除
creationProfileNo原创设定(worldview/characters/forbidden/mainConflict/genre/extra);空对象 {} 表示清除
creationProfilesNo按书原创设定;空对象 {} 表示清除
systemPromptModeNo提示档位

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changedv8.0.0
    • changedInput schema / properties / action / description
      Previous value: -"get=查看;set=修改。"New value: +"操作"
    • changedInput schema / properties / autoAnalyze / description
      Previous value: -"分析作品时是否主动使用句式分析。"New value: +"自动分析"
    • changedInput schema / properties / chatThreshold / description
      Previous value: -"实时聊天写作的提问节奏:每写多少字停下来问用户(100~5000,默认 400)。传 0 清回默认;非数字忽略。"New value: +"聊天提问字数阈值(100~5000,0=默认)"
    • changedInput schema / properties / creationProfile / description
      Previous value: -"原创模式设定(worldview/characters/forbidden/mainConflict/genre/extra 字符串键,留空项省略;空对象 {} 表示清除全部、交给模型——宿主不支持 null 类型)。"New value: +"原创设定(worldview/characters/forbidden/mainConflict/genre/extra);空对象 {} 表示清除"
    • changedInput schema / properties / creationProfiles / description
      Previous value: -"按书专属原创设定(键=书名,值=同上结构;空对象 {} 表示清除全部书的专属设定——宿主不支持 null 类型)。"New value: +"按书原创设定;空对象 {} 表示清除"
    • changedInput schema / properties / enabled / description
      Previous value: -"写作助手功能总开关。"New value: +"总开关"
    • changedInput schema / properties / features / description
      Previous value: -"功能开关(11 个键全量:emotionCaveat=情感净化预警 / genreTheme=题材与流派检测 / emotionComplexity=情感复杂度 / semanticEmbedding=本地语义增强 / semanticSearch=语义检索 / semanticStyle=语义风格距离 / semanticImplicit=意象歧义语义裁决 / rawWriting=非净化直白模式 / webnovelVibe=网文信号 / lexiconFirst=必用词优先 / chatWriting=实时聊天写作),如 { emotionCaveat: false }。注意:rawWriting=true 会跳过 UI 的双重确认+承诺输入流程,仅应在用户明确要求时开启。"New value: +"功能开关(emotionCaveat/genreTheme/emotionComplexity/semanticEmbedding/semanticSearch/semanticStyle/semanticImplicit/rawWriting/webnovelVibe/lexiconFirst/chatWriting);rawWriting仅明确要求时开。"
    • changedInput schema / properties / leanWorkflow / description
      Previous value: -"精简工作流(默认 false):true=注入最简提示词(优先于档位与场景),只保留「工具按需调用」一条原则,报告类工具未显式传 brief 时默认走精简输出。适合成本敏感的长篇。"New value: +"精简工作流(省token)"
    • changedInput schema / properties / promptScene / description
      Previous value: -"提示词场景(仅 full 档生效):general=通用写作工作流(默认,等价于 4.x 行为) / writing=写新章 / revising=改稿 / auditing=审计(只体检不改稿) / setup=建资料(只维护设定与创作资料)。"New value: +"full档场景"
    • changedInput schema / properties / styleTolerance / description
      Previous value: -"风格基线容差(每维 { low: -20, high: 20 },low 为负/高为正;空对象 {} 表示清除并恢复推荐——宿主不支持 null 类型)。"New value: +"容差;空对象 {} 表示清除"
    • changedInput schema / properties / systemPromptMode / description
      Previous value: -"系统提示词档位:off=不注入 / brief=精简(只说明有这套工具) / full=完整(按场景注入对应流程)。"New value: +"提示档位"
    • changedInput schema / properties / tools / description
      Previous value: -"各工具开关(如 { novel_plot: false }),键必须是 novel_* 工具名。"New value: +"工具开关({novel_*:bool})"
  2. Changed5 schema fields changedv7.3.3
    • changedInput schema / properties / chatThreshold / description
      Previous value: -"实时聊天写作的提问节奏:每写多少字停下来问用户(100~5000,默认 400)。传 0 或 null 清回默认;非数字忽略。"New value: +"实时聊天写作的提问节奏:每写多少字停下来问用户(100~5000,默认 400)。传 0 清回默认;非数字忽略。"
    • changedInput schema / properties / creationProfile / description
      Previous value: -"原创模式设定(worldview/characters/forbidden/mainConflict/genre/extra 字符串键,留空项省略;空对象 {} 清除全部交给模型——宿主不支持 null 类型)。"New value: +"原创模式设定(worldview/characters/forbidden/mainConflict/genre/extra 字符串键,留空项省略;空对象 {} 表示清除全部、交给模型——宿主不支持 null 类型)。"
    • changedInput schema / properties / creationProfiles / description
      Previous value: -"按书专属原创设定(键=书名,值=同上结构;空对象 {} 清除全部书的专属设定——宿主不支持 null 类型)。"New value: +"按书专属原创设定(键=书名,值=同上结构;空对象 {} 表示清除全部书的专属设定——宿主不支持 null 类型)。"
    • changedInput schema / properties / features / description
      Previous value: -"功能开关(emotionCaveat=情感净化预警 / genreTheme=题材与流派检测 / webnovelVibe=网文信号 / rawWriting=非净化直白模式 / semanticEmbedding=本地语义增强 / lexiconFirst=必用词优先),如 { emotionCaveat: false }。注意:rawWriting=true 会跳过 UI 的双重确认+承诺输入流程,仅应在用户明确要求时开启。"New value: +"功能开关(11 个键全量:emotionCaveat=情感净化预警 / genreTheme=题材与流派检测 / emotionComplexity=情感复杂度 / semanticEmbedding=本地语义增强 / semanticSearch=语义检索 / semanticStyle=语义风格距离 / semanticImplicit=意象歧义语义裁决 / rawWriting=非净化直白模式 / webnovelVibe=网文信号 / lexiconFirst=必用词优先 / chatWriting=实时聊天写作),如 { emotionCaveat: false }。注意:rawWriting=true 会跳过 UI 的双重确认+承诺输入流程,仅应在用户明确要求时开启。"
    • changedInput schema / properties / styleTolerance / description
      Previous value: -"风格基线容差(每维 { low: -20, high: 20 },low 为负/高为正;空对象 {} 清除恢复推荐——宿主不支持 null 类型,清除一律用空对象)。"New value: +"风格基线容差(每维 { low: -20, high: 20 },low 为负/高为正;空对象 {} 表示清除并恢复推荐——宿主不支持 null 类型)。"
  3. Changed1 schema field changedv7.3.0
    • addedInput schema / properties / chatThreshold
      Added value: +{
      +  "description": "实时聊天写作的提问节奏:每写多少字停下来问用户(100~5000,默认 400)。传 0 或 null 清回默认;非数字忽略。",
      +  "type": "number"
      +}
  4. Changed1 schema field changedv6.3.0
    • changedInput schema / properties / features / description
      Previous value: -"功能开关(emotionCaveat=情感净化预警 / genreTheme=题材与流派检测 / webnovelVibe=网文信号 / rawWriting=非净化直白模式 / semanticEmbedding=本地语义增强),如 { emotionCaveat: false }。注意:rawWriting=true 会跳过 UI 的双重确认+承诺输入流程,仅应在用户明确要求时开启。"New value: +"功能开关(emotionCaveat=情感净化预警 / genreTheme=题材与流派检测 / webnovelVibe=网文信号 / rawWriting=非净化直白模式 / semanticEmbedding=本地语义增强 / lexiconFirst=必用词优先),如 { emotionCaveat: false }。注意:rawWriting=true 会跳过 UI 的双重确认+承诺输入流程,仅应在用户明确要求时开启。"
  5. Changed1 schema field changedv5.1.1
    • addedInput schema / properties / leanWorkflow
      Added value: +{
      +  "description": "精简工作流(默认 false):true=注入最简提示词(优先于档位与场景),只保留「工具按需调用」一条原则,报告类工具未显式传 brief 时默认走精简输出。适合成本敏感的长篇。",
      +  "type": "boolean"
      +}
  6. Changed2 schema fields changedv5.0.0
    • addedInput schema / properties / promptScene
      Added value: +{
      +  "description": "提示词场景(仅 full 档生效):general=通用写作工作流(默认,等价于 4.x 行为) / writing=写新章 / revising=改稿 / auditing=审计(只体检不改稿) / setup=建资料(只维护设定与创作资料)。",
      +  "enum": [
      +    "general",
      +    "writing",
      +    "revising",
      +    "auditing",
      +    "setup"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / systemPromptMode
      Added value: +{
      +  "description": "系统提示词档位:off=不注入 / brief=精简(只说明有这套工具) / full=完整(按场景注入对应流程)。",
      +  "enum": [
      +    "off",
      +    "brief",
      +    "full"
      +  ],
      +  "type": "string"
      +}
  7. First observed

TDQS

C2.6/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the whole burden, and it discloses almost nothing: it does not say whether set overwrites or merges existing configuration, whether omitted fields are preserved or reset, whether changes persist across sessions, or whether any traps exist. For a 12-parameter mutation surface with nested objects, 'set 修改' is insufficient disclosure.

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?

It is a single compact sentence with the read/write framing front-loaded and zero filler. The brevity is achieved by omitting content rather than by editing it, which keeps the structure score high while the completeness score takes the hit.

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?

Twelve parameters, nested objects, three enums, no output schema and no annotations make this a complex configuration surface. The description says nothing about how the many toggle groups interact, what the defaults are, or what the return shape of a get looks like, so an agent must reconstruct behavior entirely from the schema.

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 100%, so the schema already documents every parameter, including the enum meanings and the '{ } means clear' conventions for the nested objects. The description adds only the get/set action mapping, which is the minimum baseline-3 contribution.

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?

It names a verb pair (read/write) and a resource (plugin and analysis toggle configuration), and it splits the two actions into get = query and set = modify. But the resource is described generically, and there is a close sibling named novel_settings that it never distinguishes itself from, so an agent cannot tell from the description which tool owns these settings.

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?

The parenthetical get/set mapping is the only guidance: use get to read, set to write. There is no statement of when to reach for this tool instead of novel_settings, no precondition for set (do you need a prior get?), and no note that get and set tolerate different parameter subsets.

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