Skip to main content
Glama
siweina

dsh-novel-writer

by siweina
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

novel_sentence_config

View or change sentence-pattern analysis settings for a novel-writing assistant, including enablement, auto-analysis, prompt mode, scene, and lean workflow.

Instructions

查看或修改句式模式分析的开关状态：enabled（分析功能是否可用）、autoAnalyze（分析作品时是否主动使用）、systemPromptMode（系统提示词档位 off/brief/full）、promptScene（提示词场景 general/writing/revising/auditing/setup，决定完整档下注入哪一套流程）与 leanWorkflow（精简工作流：打开后只按需调用工具，省 token）。

Input Schema

NameRequiredDescriptionDefault
toolsNo各工具开关（如 { novel_plot: false }），键必须是 novel_* 工具名。
actionNoget=查看；set=修改。
enabledNo写作助手功能总开关。
featuresNo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。
autoAnalyzeNo分析作品时是否主动使用句式分析。
promptSceneNo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）。
leanWorkflowNo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。
styleToleranceNo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）。
creationProfileNo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）。
creationProfilesNo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）。
systemPromptModeNo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）。

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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。"
  2. 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"
+}
  3. 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"
+}
  4. First observed

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral burden, and it does disclose some real traits: leanWorkflow overrides mode and scene, reports default to brief output under it, promptScene only takes effect in full mode, and defaults (false). It omits though the mutation semantics — whether setting a subset replaces or merges existing config, and the clearing behavior (which the schema documents but the prose does not).

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?

Purpose is front-loaded in the first clause, which is good, but the rest is a single run-on sentence enumerating five switches with parenthetical glosses. It covers only half the 11 parameters while being dense; it is serviceable but not tight or skimmable.

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?

For an 11-parameter, nested-object config tool with no annotations and no output schema, the description addresses 5 of 11 parameters and leaves tools, features, styleTolerance, creationProfile, and creationProfiles entirely to the schema. Since schema coverage is 100% this is workable, but the side-effect-heavy parameters (features/rawWriting, clearing behavior) get their only cautions in the schema rather than the prose.

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 baseline is 3. The prose mostly restates the schema's own parameter descriptions (enabled, autoAnalyze, promptScene, leanWorkflow, systemPromptMode) with little added syntax or format detail, so it neither compensates for nor exceeds the schema.

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 pair (查看或修改) and a scoped resource (句式模式分析的开关状态), then enumerates the concrete switches it governs. An agent can tell this is a config read/write tool for sentence-pattern analysis. It does not, however, name or differentiate against the sibling novel_settings, which is the most likely confusion point.

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 only usage cue is the implicit get/set framing of the opening sentence; there is no statement of when to reach for this tool versus novel_settings or the other novel_* config-ish siblings. No prerequisites, no when-not guidance, and the action enum (get/set) is left to the schema.

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

Deploy Server

Other Tools