Skip to main content
Glama

读飞书文档正文

feishu_doc_read
Read-only

Reads the plain-text body of a Feishu docx document from a document_id so you can summarize, excerpt, or answer questions about its content. Use it when the document token is already known.

Instructions

读取一个 docx 文档的纯文本正文(不含图片、表格结构、评论),用于总结、摘录、问答。使用场景:手上已有 document_id,想看文档写了什么。document_id 从哪来:feishu_drive_list 里 docx 条目的 token;或者知识库场景下 feishu_wiki_node 返回的 obj_token(注意是 obj_token,不是 node_token)。前置条件(重要):应用目前有 docs:doc,但没有 docx:document:readonly,读已有文档很可能返回 99991672;拿到这个错误时,需要在开放平台开通 docx:document(或只读版)并重新发布版本后才生效。不要用它读电子表格(用表格工具)或多维表格(用 feishu_bitable_* 工具)。只读,不改文档。

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": "feishu_doc_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
max_charsNo正文最多返回多少个字符,默认 20000;超出会截断并注明原文长度。
document_idYes要读的文档 token(docx 文档的 document_id),不是 URL、不是 node_token。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the real burden and does well: it discloses the content that is excluded (images, tables, comments), the truncation behavior tied to max_chars, and a concrete auth prerequisite with the expected error code 99991672 and the fix (enable docx:document and republish). What it omits is pagination/continuation behavior when truncation occurs and any hint at the response shape, which keeps it below 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?

Purpose and scope are front-loaded, then usage, then provenance, then the permission caveat, then exclusions, then a closing read-only assurance — a sensible order with no filler sentences. The permission paragraph is long and slightly repetitive ("重要", bolded), but that content is load-bearing for a likely failure mode.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read tool with no output schema and thin annotations, the description covers everything an agent needs: what content is returned, what is dropped, truncation defaults, where the ID comes from, which siblings to use instead, and the exact auth failure to expect. Nothing required to call it correctly is missing.

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 both parameters are already documented and the baseline is 3. The description adds provenance semantics the schema does not: that document_id should come from feishu_drive_list or a wiki node's obj_token, not node_token. That is genuine meaning beyond the schema, though it does not explain max_chars behavior independently of the schema's own description.

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 ("读取一个 docx 文档的纯文本正文") and immediately bounds the scope (no images, table structure, or comments). It names the sibling categories it is not (spreadsheets, bitables), so an agent can separate it from feishu_sheet_read and feishu_bitable_* without opening any schema.

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?

It states the triggering condition ("手上已有 document_id,想看文档写了什么") and gives explicit when-not guidance: do not use this for spreadsheets or bitables, and it names the tools to use instead. It also tells the agent where a valid document_id comes from (feishu_drive_list tokens, or feishu_wiki_node obj_token rather than node_token), which removes the most likely mis-call.

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