Skip to main content
Glama
Google Workspace MCP Server - Control Gmail, Calendar, Docs, Sheets, Slides, Chat, Forms & Drive

Google Workspace MCP Server - Control Gmail, Calendar, Docs, Sheets, Slides, Chat, Forms & Drive

Get Script Project

get_script_project
Read-onlyIdempotent

List Apps Script projects and retrieve metadata, file overview, or complete source file content using script and file IDs.

Instructions

Read Apps Script projects and their source files.

Actions: - "list": List Apps Script projects accessible to the user (Drive-backed). Optional: page_size, page_token. - "get": Retrieve one project's metadata and file overview, or one complete source file when file_name is provided. Requires script_id.

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": {
      "user_google_email": "<user_google_email>",
      "action": "<action>"
    },
    "name": "get_script_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesOne of "list", "get".
file_nameNoOptional source file name for get.
page_sizeNoNumber of results per page for list (default: 50).
script_idNoThe script project ID (required for get).
page_tokenNoPagination token for list (optional).
user_google_emailYesUser's email address

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.28.0
    • addedInput schema / properties / action
      Added value: +{
      +  "description": "One of \"list\", \"get\".",
      +  "type": "string"
      +}
    • addedInput schema / properties / file_name
      Added value: +{
      +  "default": null,
      +  "description": "Optional source file name for get.",
      +  "type": "string"
      +}
    • addedInput schema / properties / page_size
      Added value: +{
      +  "default": 50,
      +  "description": "Number of results per page for list (default: 50).",
      +  "type": "integer"
      +}
    • addedInput schema / properties / page_token
      Added value: +{
      +  "default": null,
      +  "description": "Pagination token for list (optional).",
      +  "type": "string"
      +}
    • addedInput schema / properties / script_id / default
      Added value: +null
    • changedInput schema / properties / script_id / description
      Previous value: -"The script project ID"New value: +"The script project ID (required for get)."
    • changedInput schema / required
      Previous value: -[
      -  "user_google_email",
      -  "script_id"
      -]New value: +[
      +  "user_google_email",
      +  "action"
      +]
  2. Addedv1.0.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds useful behavior beyond that: listing is Drive-backed (implying access scope), 'get' requires script_id, and providing file_name returns an entire source file rather than an overview.

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?

The action-list structure is front-loaded and scannable, with each bullet stating the action and its requirements. Wording is tight, with only minor redundancy between the opener and the per-action parameter notes.

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?

Output schema exists, so return-value explanation is unnecessary, and the description covers both actions and their required parameters for a six-parameter tool. Minor gaps remain around error conditions and what the Drive-backed listing actually contains, but nothing critical for correct invocation is missing.

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 the schema already documents every parameter and the baseline is 3. The description adds some conditional meaning, notably that file_name triggers a full file return and that page_size/page_token belong only to 'list', but it introduces no syntax, format, or constraint detail beyond the schema.

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?

The description opens with a specific verb and resource ("Read Apps Script projects and their source files") and then enumerates the two actions, so an agent knows exactly what is retrievable. It does not explicitly contrast itself with the manage_script_project or manage_script_content siblings, so sibling differentiation is only implied by the read-vs-manage naming.

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

Usage Guidelines3/5

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

It clearly distinguishes the two actions: 'list' for enumeration and 'get' for one project, with file_name switching 'get' into full-source-file mode. There is no when-not guidance or explicit pointer to sibling tools for adjacent operations such as deployments, versions, or content mutation.

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