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

Batch Update Presentation

batch_update_presentation
Destructive

Apply multiple updates to a Google Slides presentation in one call, including adding slides, shapes, text, images, styling, and deleting objects.

Instructions

Apply batch updates to a Google Slides presentation.

Important: Each request object must contain exactly one supported Slides request type, such as createSlide, createShape, insertText, updateTextStyle, createImage, or deleteObject.

insertText.objectId must be a text-capable shape or table object ID,
not a slide/page object ID. To add text to a slide, create a text box
or shape first with createShape, set elementProperties.pageObjectId to
the slide ID, and then insertText into that shape objectId. To edit
existing text, call get_presentation with action="page" and use a
Shape or Table element ID.

To write speaker (presenter) notes, call get_presentation with
action="page" to get the slide's speaker notes shape ID, then target
that ID: deleteText with textRange {"type": "ALL"} to clear
the existing notes (omit this when they are already empty, which errors),
followed by insertText at insertionIndex 0. The notes page ID is not a
valid target.

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>",
      "presentation_id": "<presentation_id>",
      "requests": "<requests>"
    },
    "name": "batch_update_presentation"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestsYesList of update requests to apply.
presentation_idYesThe ID of the presentation to update.
user_google_emailYesThe user's Google email address. Required.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, and non-idempotent, so the risk profile is covered structurally. The description adds real behavioral detail that the annotations do not: each request object must contain exactly one supported request type, and clearing notes that are already empty will error. It does not address whether the batch is applied atomically, what happens on partial failure, or whether ordering within the array matters, which is important for a destructive batch operation.

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?

Purpose is front-loaded in one sentence, followed by an 'Important:' block that groups the non-obvious object-shape rules and then the two ID-targeting recipes. Each paragraph covers a distinct failure mode an agent would otherwise hit, so nothing reads as filler despite the length.

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 an output schema present, return values need not be explained, and the description covers the genuinely hard parts: request object shape and object-ID targeting for text and speaker notes. Remaining gaps are atomicity/rollback behavior and any batch-size or permission constraints, which for a destructive batch call an agent would benefit from knowing.

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%, and user_google_email and presentation_id are adequately described in the schema. The critical parameter is `requests`, whose schema is an untyped array of free-form objects with only 'List of update requests to apply'; the description compensates substantially by specifying that each object holds exactly one request type and by spelling out ID-targeting rules (slide/page IDs vs. shape/table IDs, notes shape IDs). That is meaningful semantics 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: 'Apply batch updates to a Google Slides presentation', and then immediately enumerates the concrete request types accepted (createSlide, createShape, insertText, updateTextStyle, createImage, deleteObject). That is more specific than the title alone and lets an agent distinguish it from read-oriented siblings like get_presentation, though it never explicitly frames itself in relation to the other batch_update_* siblings.

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?

It gives clear, actionable routing: to add text to a slide, create a shape first with createShape and set elementProperties.pageObjectId; to edit existing text or write speaker notes, call get_presentation with action="page" first. Those are explicit when-to-use-this-vs-another-tool instructions. What is missing is any negative guidance, such as when a single-object edit path would be preferable or what limits apply to batch size.

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