Skip to main content
Glama

查知识库节点

feishu_wiki_node
Read-only

Retrieve a Feishu wiki node by node_token or obj_token, or list root nodes for a space_id. Use the returned obj_token to read the underlying document or sheet; node_token is only for wiki navigation.

Instructions

知识库节点查询:给 token 就查这个节点(node_token 或 obj_token 都行),给 space_id 而不给 token 就列出该空间的根节点。使用场景:从知识库链接里拿到一段 token,需要知道它对应哪篇文档/哪张表;或者要遍历某个空间有哪些内容。关键点:返回里的 obj_token 才是真正文档/表格的 token——读内容、读表要用 obj_token;node_token 只用于继续在 wiki 里翻节点,传给 feishu_doc_read 会失败。前置条件:应用需被加入该知识库并有 wiki 读权限。只读,不改节点。

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": "feishu_wiki_node"
  }
}

Input Schema

NameRequiredDescriptionDefault
tokenNo知识库节点的 token(node_token 或 obj_token)。给了它就直接查这一个节点。
space_idNo知识库空间 ID。只有给了 space_id 且没给 token 时,才用它列出该空间的根节点。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, yet the description still adds real value: the wiki-read permission prerequisite and the critical node_token vs obj_token distinction, including that node_token passed to feishu_doc_read will fail. It does not cover error behavior or how child nodes are reached, so it stops 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 operation, then clearly labeled 使用场景 / 关键点 / 前置条件 sections that make it scannable. The closing '只读,不改节点' restates readOnlyHint and is the only low-value sentence, but the whole thing is still compact.

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?

With only 2 optional params and no output schema, this covers the modes, prerequisites, and the return-field semantics that matter most. The gap is traversal depth: the stated use case of walking a space's contents is not reconciled with the tool only listing root nodes, and no guidance is given on going deeper.

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 the baseline is 3, but the description goes beyond the schema by explaining what each token type is for downstream: obj_token is the one to use for reading content or tables, while node_token only continues wiki traversal. That downstream meaning is not derivable from the schema text alone.

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 plus two explicit modes: with token, look up that one node (node_token or obj_token); with only space_id, list that space's root nodes. It also names the sibling it hands off to (feishu_doc_read), so an agent can distinguish it from feishu_wiki_spaces and the doc/bitable tools 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?

Gives concrete scenarios: a token extracted from a wiki link whose document/sheet is unknown, or enumerating what a space contains. The token-vs-space_id choice is spelled out with the exact condition ('space_id but no token'), leaving nothing to infer.

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