Skip to main content
Glama
Sign In
mmm-mcp-server

mmm-mcp-server

by nhorie-canal
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

create_document

Creates a new Markdown document in a mind map at the top level or under a chosen parent element, enabling readable notes and diagrams to be added to the map.

Instructions

マップに、Markdownの文書(MD文書)を新しく作る。指定した要素の子の末尾に、文書の要素を1つ足す(parentElementIdを省略またはnullにすると、マップの最上位の末尾)。作った文書の要素は、アプリでは書類のアイコンとタイトルで見える(タップすると整形した文書が開く。```mermaid のブロックは図になる)。中身はread_documentで読める。既存の文書の書き換えはupdate_documentを使う(これは新しく作るだけ)。contentはMarkdown(UTF-8で1000000バイトまで。超えると何も書かずにエラーを返す)。titleを省略すると、contentの最初の見出し(# の行)、無ければ最初の行がタイトルになる。追加先(parentElementId)はlist_elementsの結果を見て判断すること。

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": {
      "mapId": "<mapId>",
      "content": "<content>"
    },
    "name": "create_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
mapIdYeslist_mapsで得たマップのID
titleNo行に見せるタイトル。省略するとcontentの最初の見出しから決める
contentYes文書の中身(Markdown)
parentElementIdNoこの要素の内側(子)の末尾に足す。マップの最上位に足す場合はnullまたは省略

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does well: it discloses the 1,000,000-byte UTF-8 cap, that exceeding it returns an error without writing anything (atomicity), the title-derivation fallback, and the UI side effect (document icon/title, tappable formatted view, mermaid blocks rendered as diagrams). The one gap is that it never says what the call returns (e.g. the new element's ID), which matters most precisely because there is no output schema.

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?

Purpose and placement come first, then behavioral rules, then alternatives — a sensible front-loading. It is a dense single block with parenthetical asides; nothing is redundant, but scannability suffers slightly versus a structured layout.

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 an unannotated mutation tool with no output schema, it covers placement, limits, error behavior, title derivation, and discoverability of the result via read_document. Only the return value of the call itself is left unspecified.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description earns above that by adding the byte limit and no-partial-write error behavior for content, the precise title fallback chain (first '# ' heading, else first line), and the instruction to consult list_elements before choosing parentElementId.

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?

States a specific verb and resource ('マップに、Markdownの文書(MD文書)を新しく作る') and immediately binds the operation to a placement rule (child tail of parentElementId, or map root). It explicitly separates itself from siblings by naming read_document for reading content and update_document for rewriting existing documents.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use and when-not-to-use: 'これは新しく作るだけ' with update_document as the alternative for edits, read_document for reading back, and list_elements to determine the insertion point. An agent has no inference left to do about which tool to pick.

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