Skip to main content
Glama

save_story_draft

Creates a new story draft or updates an existing one by merging only the specified changes, then validates character and count limits before saving and reports any overages.

Instructions

스토리를 임시저장한다 (공개/수정 반영은 사이트에서 직접). storyId가 있으면 최신 임시저장본(없으면 공개본)을 불러와 changes만 덮어쓴다. storyId가 없으면 새 스토리를 만든다. changes 키는 get_story 출력과 같은 이름 (name, simpleDescription, description, detailDescription, customPrompt, startingSets 등). 저장 전에 크랙 제한을 검사해 넘으면 저장하지 않고 초과 항목을 알려준다. 주요 제한: 이름 2~30자, 한 줄 소개 30자, 프롬프트 7000자, 시작설정 이름 12자·프롤로그 1000자·시작 상황 1000자·추천 답변 3개×200자, 시작설정 최대 3개, 키워드북 시작설정당 20개·키워드 5개×10자·정보 400자, 해시태그 10개×10자. 전체 표는 get_limits.

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": {
      "changes": "<changes>"
    },
    "name": "save_story_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
storyIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does so well: it discloses merge-not-replace semantics, the fallback from draft to published version, creation behavior when storyId is absent, and that validation runs before saving with rejection plus a report of offending fields. It omits the success response shape and any permission/auth requirements, which keeps it short of a 5.

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?

Front-loaded with the action, then the storyId branch, then the changes key mapping, then validation. The enumerated limit list is long but operationally useful before a save; since it defers the full table to get_limits, it could have been trimmed slightly.

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?

For a two-parameter mutation tool with no annotations and no output schema, the description covers merge semantics, creation path, pre-save validation, and the key constraints an agent must satisfy. Return values and authentication are the remaining gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and 'changes' is a free-form object, yet the description explains that its keys mirror the get_story output (naming name, simpleDescription, description, customPrompt, startingSets) and defines storyId's two distinct behaviors. This is substantial meaning added beyond what the bare schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The definition opens with a specific verb and resource ('스토리를 임시저장한다') and immediately scopes it against publishing/modification ('공개/수정 반영은 사이트에서 직접'), so an agent knows this is a draft-only write path and not the publish path.

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?

It clearly states the branch condition for use: with storyId it merges into the latest draft or published version, without storyId it creates a new story. It also routes the agent to get_limits for the full constraint table, though it never states when to prefer this over siblings such as get_story_draft or list_story_drafts.

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