Skip to main content
Glama
Google Workspace MCP connector

Google Workspace MCP connector

by animesh-ex

sheets_write

Write values or formulas to a specified Google Sheets range, starting from a cell like Sheet1!B2; formulas such as =SUM(A1:A9) are evaluated automatically.

Instructions

Write values to a range (starting cell like 'Sheet1!B2' is enough). Formulas like '=SUM(A1:A9)' are evaluated.

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": {
      "spreadsheetId": "<spreadsheetId>",
      "range": "<range>",
      "values": "<values>"
    },
    "name": "sheets_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNotrue = store literally, don't parse formulas/numbers
rangeYes
valuesYes
spreadsheetIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true. The description adds real behavioral context the annotations don't carry: formulas are evaluated and a single starting cell is accepted. It stops short of the most consequential behavior for a writer — whether values outside the provided block are overwritten or preserved, given destructiveHint=false.

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?

Two short sentences, front-loaded with the action and immediately followed by the practical range hint and formula note. No filler or repetition.

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?

A four-parameter write tool with no output schema needs little more than this; the formula and range-start hints cover the main caller pitfalls. The remaining gap is the shape of `values`, which an agent must read from the schema's nested array definition.

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 coverage is only 25%, with just `raw` documented in the schema. The description compensates partly by explaining the `range` format with a worked example, but says nothing about `values` being a 2-D array (array of rows) or what `raw` means for formula parsing.

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 (write values to a range) and clarifies that a starting cell like 'Sheet1!B2' suffices, so an agent knows it need not supply an end cell. It does not contrast itself with the sibling sheets_append_rows, so the agent must infer whether to write or append.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance is given, and no alternatives are named. The description never says whether existing values in the target range are replaced, nor points to sheets_append_rows or sheets_batch_update for adjacent tasks.

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