Skip to main content
Glama
Sign In
dsh-novel-writer

dsh-novel-writer

by siweina
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

novel_plot

Track a novel’s foreshadowing and plot hooks, mark them open or resolved, and link chapters, characters, priorities, and payoff conditions for continuity.

Instructions

伏笔/剧情线登记表：维护某部作品的伏笔与剧情钩子（open 待回收 / done 已回收）。

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": {
      "book": "<book>"
    },
    "name": "novel_plot"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo伏笔 id（update/done/delete 时需要）。
bookYes书名。
noteNo可选：备注（如何回收/何时回收）。
rootNo章节库根目录。
typeNo可选：伏笔类型（add/update）。
actionNolist=查看；add=登记新伏笔；update=修改；done=标记已回收；delete=删除；scan=扫描章节文本，自动更新伏笔提及章节；graph=跨章结构视图（伏笔埋设跨度 / 人物连续缺席 / 剧情线活跃度 / 时间线顺序 / 大纲对比），只读不写盘。
statusNoupdate 时可选：把伏笔重新打开（open）或标记已回收（done）。用于误操作回退；与 action="done" 等价的效果优先用 done。
chapterNo可选：伏笔出现的章节。
contentNoadd/update 时：伏笔内容描述。
priorityNo可选：优先级（add/update）。
locationsNo可选：关联地点（add/update）。
payoffConditionNo可选：回收条件（add/update）。
absenceThresholdNograph 时可选：人物连续缺席多少章算异常（默认 5）。
relatedCharactersNo可选：关联人物（add/update）。

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv7.1.0
    • addedInput schema / properties / status
      Added value: +{
+  "description": "update 时可选：把伏笔重新打开（open）或标记已回收（done）。用于误操作回退；与 action=\"done\" 等价的效果优先用 done。",
+  "enum": [
+    "open",
+    "done"
+  ],
+  "type": "string"
+}
  2. Changed3 schema fields changedv5.0.0
    • addedInput schema / properties / absenceThreshold
      Added value: +{
+  "description": "graph 时可选：人物连续缺席多少章算异常（默认 5）。",
+  "type": "integer"
+}
    • changedInput schema / properties / action / description
      Previous value: -"list=查看；add=登记新伏笔；update=修改；done=标记已回收；delete=删除；scan=扫描章节文本，自动更新伏笔提及章节。"New value: +"list=查看；add=登记新伏笔；update=修改；done=标记已回收；delete=删除；scan=扫描章节文本，自动更新伏笔提及章节；graph=跨章结构视图（伏笔埋设跨度 / 人物连续缺席 / 剧情线活跃度 / 时间线顺序 / 大纲对比），只读不写盘。"
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "list",
-  "add",
-  "update",
-  "done",
-  "delete",
-  "scan"
-]New value: +[
+  "list",
+  "add",
+  "update",
+  "done",
+  "delete",
+  "scan",
+  "graph"
+]
  3. 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 full behavioral burden, and it says nothing about which actions write to disk, that 'delete' is destructive, or that 'scan' silently mutates mention records. The two most behaviorally distinct modes (scan and graph) are entirely absent from the description — graph's read-only nature is disclosed only inside the action enum in the schema, not here.

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 front-loaded sentence that names the resource first and uses a colon to attach the status legend; there is no filler or redundancy. It is economical, though the brevity tips into under-specification for a 14-parameter tool.

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?

For a tool with 14 parameters, seven action modes, mutation and deletion paths, and no annotations or output schema, the description covers only the CRUD-registry metaphor. An agent would not learn from it that 'graph' produces a read-only cross-chapter structural report or that 'scan' rewrites mention chapters — the two capabilities most likely to be misused or overlooked.

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%, including per-enum-value explanations for action and status, so the baseline is 3. The description adds no parameter-level meaning beyond what the schema already documents — the open/done gloss it provides is already present in the status field's own description.

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?

The description identifies a specific resource — a foreshadowing/plot-hook registry for a given work — and the parenthetical clarifies the open/done lifecycle. But the verb '维护' (maintain) is generic, and the description never reveals that the tool actually exposes seven distinct actions including text scanning and a cross-chapter structural graph view. It also gives no signal distinguishing it from siblings like novel_outline or novel_continuity_check.

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?

Only the status semantics (open = unrecovered, done = recovered) are explained; there is no statement of when to reach for this tool versus novel_outline, novel_continuity_check, or novel_summary, all of which touch plot structure. No prerequisites, no exclusions, no workflow context for choosing an action.

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