Skip to main content
Glama
siweina

dsh-novel-writer

by siweina
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

novel_settings

Maintain five setting tables per book — characters, locations, items, timeline, worldview: list, add, update, delete, or scan entries by category, and detect the cultural baseline.

Instructions

设定管理（五张表：人物/地点/道具/时间线/世界观用语规范），list/add/update/delete/scan 按 category 维护，detect 自动判断文化基准。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dayNotimeline 专用：时间点标识（add 时作为条目名登记；update/delete 用 name=旧标识 定位，改名时同时传 day=新标识）。
bookYes书名。
nameNo条目名（人物名/地名/道具名；timeline 用 day 字段）。
rootNo章节库根目录。
aliasNocharacter 专用：别名。
basisNoworldview 专用：判断依据/文化基准说明。
eventNotimeline 专用：事件。
notesNo可选：备注。
ownerNoitem 专用：当前持有者。
actionNolist=查看；add=登记；update=修改；delete=删除；scan=扫描章节提取候选；detect=自动判断世界观文化基准（worldview 专用）。
ritualNoworldview 专用：仪式规范（如'点烛不烧香'）。
statusNoitem 专用：状态（如 在琉璃处/已遗失）。
traitsNocharacter 专用：性格/外貌特征。
chapterNotimeline 专用：对应章节。
categoryNo表类别（character/location/item/timeline/worldview；list/add/update/delete/scan 需要；detect 固定 worldview）。
lastSeenNoitem 专用：最近出现的章节。
firstSeenNo可选：首次出现的章节。
allowWordsNoworldview 专用：本书用词豁免（逐词静音）。登记后这些词在**本书**不再报用语冲突（禁用词与 speechStyle.honorBad 两路都会静音），且**只作用于本书**——不提供全局静音，词仍留在词表里、别的书照常检查。用于「这个词在这本书里本来就是对」的情况：例：修仙小说里的「修士」、中文历史小说里的「教堂」。用法：novel_settings add category=worldview name="用词豁免" allowWords=["修士"]。
bannedWordsNoworldview 专用：禁用词表（如欧式背景禁 上香/老夫）。
descriptionNo可选：描述。
recommendedNoworldview 专用：替代词映射（如 { "上香": "点烛" }）。
speechStyleNoworldview 专用：说话方式规范（title 称谓/honorBad 客套禁词/ritualBadPatterns 仪式禁式/tone 语气·整体为 JSON 对象）。
relationshipsNocharacter 专用：人际关系。

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv6.6.0
    • addedInput schema / properties / allowWords
      Added value: +{
+  "description": "worldview 专用：本书用词豁免（逐词静音）。登记后这些词在**本书**不再报用语冲突（禁用词与 speechStyle.honorBad 两路都会静音），且**只作用于本书**——不提供全局静音，词仍留在词表里、别的书照常检查。用于「这个词在这本书里本来就是对」的情况：例：修仙小说里的「修士」、中文历史小说里的「教堂」。用法：novel_settings add category=worldview name=\"用词豁免\" allowWords=[\"修士\"]。",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  2. First observed

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It does not disclose that add/update/delete mutate persistent state, whether deletes are reversible, what scan actually does to the chapter library, or what detect changes. Listing the tables is organization, not behavioral disclosure, leaving significant gaps for a 23-parameter mutating tool.

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 densely packed sentence that front-loads the resource and then the action vocabulary; nothing is wasted. It is arguably too terse for the tool's complexity, but there is no filler or redundancy.

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 23-parameter, multi-action, mutating tool with no output schema and no annotations, a one-sentence description is insufficient: it never explains what add/update/delete persist, what scan returns or where candidates go, or what detect's '文化基准' output is used for. The rich parameter schema compensates partially but the behavioral picture remains incomplete.

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%, and the schema itself richly documents every field (including a detailed allowWords explanation and per-action semantics), so the baseline of 3 applies. The description adds only the mapping of the five category values, which is already present in the category enum description.

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 resource (five settings tables: character/location/item/timeline/worldview) and enumerates the six operations, so an agent knows this is the CRUD hub for story-bible data. It does not however distinguish itself from siblings like novel_continuity_check or novel_lexicon, which one might plausibly confuse with '设定管理'.

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 the actions are dispatched 'by category' and that detect judges the cultural baseline, which implies usage, but there is no explicit when-to-use vs alternatives guidance and no mention of prerequisites (e.g. root/book setup, when scan is appropriate versus reading chapters).

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