Skip to main content
Glama
Sign In
moki-whiteboard

moki-whiteboard

by JKZeng-cell
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

导出白板快照

whiteboard_export
Read-only

Exports a whiteboard snapshot and .moki download URL, or returns a self-contained Base64 ZIP with images and files when includeArchive is true; use app or HTTP export for boards over 8 MiB.

Instructions

Export a snapshot and .moki download URL (requires the HTTP API). With includeArchive=true, return a self-contained Base64 ZIP with images/files, up to 8 MiB; use app or HTTP export for larger boards. 返回完整快照和 .moki ZIP 下载地址（下载需要 API）。includeArchive=true 时直接返回含图片/文件的归档 Base64，无需 API；归档最多 8 MiB，较大白板请通过应用导出。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "whiteboard_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
boardIdNo白板 ID；省略时使用最近更新的白板，建议始终指定准确 IDdefault
includeArchiveNo

Output Schema

NameRequiredDescriptionDefault
boardNo
errorNo
boardsNo
pageIdNo
boardIdNo
currentNo
deletedNo
versionNo
alignedIdsNo
deletedIdsNo
elementIdsNo
updatedIdsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.7

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint; the description adds genuinely new operational facts beyond them — the HTTP API dependency for the download URL, the 8 MiB cap on archives, and the larger-board workaround. It does not mention pagination or error behavior, keeping 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is front-loaded and every claim is substantive, but the entire passage is duplicated verbatim in English and Chinese, roughly doubling length for a two-sentence tool. The redundancy costs space without adding information.

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?

An output schema exists, yet the description still usefully characterizes both return shapes (download URL vs inline Base64). With the size limit, API prerequisite, and fallback covered, an agent has enough to call it correctly; only the empty-archive/error case is unaddressed.

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 50%, with includeArchive undocumented in the schema; the description compensates by explaining exactly what that flag changes and its size constraint. boardId is covered by the schema description, so nothing critical is left ambiguous.

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 and resource: export a snapshot plus a .moki download URL, and returns an archive when includeArchive=true. The two output modes are named clearly; it only lacks explicit differentiation from siblings such as whiteboard_inspect or whiteboard_duplicate.

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?

Gives a clear mode-selection rule (includeArchive=true → self-contained Base64 archive, no API) and an explicit escalation path for boards over 8 MiB ('use app or HTTP export'). It does not say when to prefer whiteboard_inspect over exporting, so the sibling routing is incomplete.

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