Skip to main content
Glama
Sign In
feishu-user-plugin

feishu-user-plugin

by EthanQC
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

read_doc_markdown

Reduce token usage for RAG and summarization by reading a Feishu document as Markdown. Accepts doc token, wiki token, or full URL. Embedded images appear as placeholders.

Instructions

[Plugin v1.3.9] Read a Feishu doc as Markdown (vs get_doc_blocks JSON). Saves ~60% tokens for RAG / digest / summarisation use cases. Accepts native docx token, wiki node token, or full Feishu URL. Embedded images / files appear as feishu://image_token/ placeholders — call download_doc_image for the binary if needed.

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": {
      "document_id": "<document_id>"
    },
    "name": "read_doc_markdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
document_idYesdocx token / wiki node / full URL

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.10

TDQS

A4.2/5.0
Behavior4/5

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

The description discloses that embedded images/files appear as placeholder tokens and that download_doc_image is needed for binaries, which is specific behavioral information. With no annotations provided, the description carries the burden and does a good job of explaining the output format and token savings. It doesn't mention potential errors or permission requirements, but for a read operation this is substantial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

The description is two concise sentences, front-loaded with purpose, followed by token savings, input types, and output placeholder behavior. Every clause adds value, and the dash structure efficiently connects the main functionality to the caveat.

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?

Given the tool has a single parameter and no output schema, the description covers the essential context: what it does, when to use it, input formats, and how to handle embedded media. It could mention potential limitations or error scenarios, but for the tool's complexity, it is quite complete.

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?

The schema already fully describes document_id as 'docx token / wiki node / full URL', and the description repeats this with slightly different wording. The description adds no additional parameter-level details such as examples, format validation, or optional flags, so it meets the baseline but doesn't exceed it.

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 description clearly identifies the tool as reading a Feishu doc as Markdown, explicitly contrasting with get_doc_blocks JSON format. The verb 'Read' and resource 'Feishu doc' are specific, and the mention of token savings reinforces the use case.

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?

The description states this is for RAG/digest/summarisation use cases and contrasts with get_doc_blocks, giving clear context for when to use it. It also directs to download_doc_image for embedded binary content. However, it doesn't explicitly list exclusions or when to prefer alternatives beyond the one mention.

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