Skip to main content
Glama

读电子表格单元格

feishu_sheet_read
Read-only

Reads values from a specified A1 range in a Feishu spreadsheet and returns a two-dimensional array of rows and columns, including formula results.

Instructions

按 A1 区间读一个电子表格的值,返回二维数组(行 × 列)。区间写法:Sheet1!A1:D20(带表名更稳),或 A1:D20(默认第一个工作表)。读整列可以用 Sheet1!A:A。只能读值和公式结果,读不到样式、批注、合并单元格信息。配合 feishu_sheet_create 新建表;写入目前没有开放(飞书的写入接口要求先拿到 sheet_id,需要先读一次拿元数据,暂未支持)。

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": {
      "spreadsheet_token": "<spreadsheet_token>",
      "range": "<range>"
    },
    "name": "feishu_sheet_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
rangeYesA1 区间,如 "Sheet1!A1:D20" 或 "A1:D20";整列写 "Sheet1!A:A"
spreadsheet_tokenYes电子表格的 token(sheet 链接里 /sheets/ 后面那串)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavior beyond that by specifying the return type, that only values and formula results come back (no styles, comments, or merged-cell info), and why write access is unavailable. It stops short of covering empty ranges, size limits, or permission errors.

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?

Core purpose and return shape are front-loaded, then range syntax, then limitations. The trailing parenthetical about Feishu write APIs requiring a prior read for sheet_id is somewhat verbose and tangential to calling this tool, keeping it from a 5.

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 a two-parameter read-only tool with no output schema, the description covers purpose, syntax, return shape, and key limitations, which is nearly everything needed. Missing only edge-case guidance such as behavior on empty or oversized ranges.

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?

Schema description coverage is 100%, so both parameters are already documented, and the description largely repeats the range examples. The only added meaning is the advice that including the sheet name is more reliable; spreadsheet_token gets no clarification beyond the schema's own link hint.

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 (read spreadsheet values by A1 range) and the return shape (two-dimensional row × column array). It also rules out writing and points to feishu_sheet_create, which separates it from the write/create siblings, but it never mentions feishu_sheet_meta, so an agent must still guess where metadata-only queries belong.

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 concrete invocation context: use a qualified range (Sheet1!A1:D20) for reliability, bare A1:D20 for the first worksheet, and Sheet1!A:A for whole columns. It also states writing is not supported yet, which prevents a dead-end attempt, but there is no explicit 'use X instead' routing for metadata or styling questions.

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