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 Presentation

get_presentation
Read-onlyIdempotent

Read a Google Slides deck to list its slides and layouts, get one slide's element IDs and text, or export a slide as JSON with geometry and styles.

Instructions

Read a deck: action "deck" (default) lists its slides and layouts, "page" gives one slide's element IDs and all its text (start here for content), "markup" gives one slide's elements as compact JSON with geometry and styles, "layouts" lists every layout.

Actions: - "deck": Title, URL, revision, and per slide its ID, title, layout, element counts and notes length; then the deck's layouts with the placeholders each provides. Lists 100 slides per call; a longer deck ends with the offset to call again with. Uses offset. - "layouts": Every layout, grouped by master, with its placeholders and the slides using it. Only needed when "deck" says there are more layouts than it lists. Uses after. - "page": Every element on one slide with its ID, in z-order, groups nested, with all text, table cells, image sources and speaker notes. No geometry or styling. Requires page_id. - "markup": One slide, or chosen elements, as JSON: boxes in points ({"x","y","w","h"}), text as paragraphs and runs, styles in a shared "styles" table referenced by "s", only locally set properties. A shape with no "shape" key is a TEXT_BOX. Requires page_id; uses targets and raw.

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>"
    },
    "name": "get_presentation"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNoFor "markup": return the Slides API Page resource itself (EMU, transforms, text indices), limited to targets when given, for writing raw batch_update_presentation requests. A target in a group keeps its group-relative transform. Defaults to False.
afterNoFor "layouts": a slide ID, or "start". Lists only the layouts of the master in use at that position, which are the only ones a new slide inserted there can use.
actionNo"deck" (default): slides and layouts. "page": one slide's element IDs and text. "markup": one slide's elements as JSON with geometry and styles. "layouts": every layout.deck
offsetNoFor "deck": index of the first slide to list, from the note at the end of a previous call. Defaults to 0.
page_idNoSlide (or any page) object ID, from "deck". Required for "page" and "markup".
targetsNoFor "markup": element IDs to return instead of the whole slide, plus "notes" for the speaker notes. A target inside a group comes back with page coordinates and its "group" ID; a group comes back with its children.
presentation_idYesThe ID of the presentation.
user_google_emailYesThe user's Google email address. Required.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv2.5.0
    • addedInput schema / properties / action
      Added value: +{
      +  "default": "deck",
      +  "description": "\"deck\" (default): slides and layouts. \"page\": one\nslide's element IDs and text. \"markup\": one slide's elements as\nJSON with geometry and styles. \"layouts\": every layout.",
      +  "type": "string"
      +}
    • addedInput schema / properties / after
      Added value: +{
      +  "default": null,
      +  "description": "For \"layouts\": a slide ID, or \"start\". Lists\nonly the layouts of the master in use at that position, which are\nthe only ones a new slide inserted there can use.",
      +  "type": "string"
      +}
    • removedInput schema / properties / include_geometry
      Removed value: -{
      -  "default": false,
      -  "description": "Also list each slide's elements with their\nplacement - transform (translate, and scale/shear when not identity)\nand intrinsic size, in raw EMU. Set this when adding slides to an\nexisting deck so new elements can match its established margins and\ncontent width. Defaults to False.",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / include_speaker_notes
      Removed value: -{
      -  "default": false,
      -  "description": "Also report each slide's speaker (presenter)\nnotes and the object ID of the shape holding them. Pass True when you\nneed to read or edit notes: that shape ID is the only valid target for\ninsertText/deleteText on notes, and batch_update_presentation writes\nnotes by deleting the shape's existing text and inserting new text.\nDefaults to False.",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / include_styles
      Removed value: -{
      -  "default": false,
      -  "description": "Also list each slide's elements with text styling\n(see get_page). Defaults to False.",
      -  "type": "boolean"
      -}
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "For \"deck\": index of the first slide to list, from the\nnote at the end of a previous call. Defaults to 0.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / page_id
      Added value: +{
      +  "default": null,
      +  "description": "Slide (or any page) object ID, from \"deck\".\nRequired for \"page\" and \"markup\".",
      +  "type": "string"
      +}
    • changedInput schema / properties / presentation_id / description
      Previous value: -"The ID of the presentation to retrieve."New value: +"The ID of the presentation."
    • changedInput schema / properties / raw / description
      Previous value: -"Return the complete Slides API Presentation resource as JSON\n(slides, layouts, masters, notes, every element and style) instead\nof the summary. Nothing is filtered, so it can be large; prefer\nget_page with raw=True for a single slide. Overrides the other flags."New value: +"For \"markup\": return the Slides API Page resource itself\n(EMU, transforms, text indices), limited to targets when given,\nfor writing raw batch_update_presentation requests. A target in a\ngroup keeps its group-relative transform. Defaults to False."
    • addedInput schema / properties / targets
      Added value: +{
      +  "default": null,
      +  "description": "For \"markup\": element IDs to return\ninstead of the whole slide, plus \"notes\" for the speaker notes.\nA target inside a group comes back with page coordinates and its\n\"group\" ID; a group comes back with its children.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. Changed2 schema fields changedv1.30.1
    • addedInput schema / properties / include_styles
      Added value: +{
      +  "default": false,
      +  "description": "Also list each slide's elements with text styling\n(see get_page). Defaults to False.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / raw
      Added value: +{
      +  "default": false,
      +  "description": "Return the complete Slides API Presentation resource as JSON\n(slides, layouts, masters, notes, every element and style) instead\nof the summary. Nothing is filtered, so it can be large; prefer\nget_page with raw=True for a single slide. Overrides the other flags.",
      +  "type": "boolean"
      +}
  3. Changed1 schema field changedv1.26.0
    • addedInput schema / properties / include_geometry
      Added value: +{
      +  "default": false,
      +  "description": "Also list each slide's elements with their\nplacement - transform (translate, and scale/shear when not identity)\nand intrinsic size, in raw EMU. Set this when adding slides to an\nexisting deck so new elements can match its established margins and\ncontent width. Defaults to False.",
      +  "type": "boolean"
      +}
  4. Changed1 schema field changedv1.24.0
    • addedInput schema / properties / include_speaker_notes
      Added value: +{
      +  "default": false,
      +  "description": "Also report each slide's speaker (presenter)\nnotes and the object ID of the shape holding them. Pass True when you\nneed to read or edit notes: that shape ID is the only valid target for\ninsertText/deleteText on notes, and batch_update_presentation writes\nnotes by deleting the shape's existing text and inserting new text.\nDefaults to False.",
      +  "type": "boolean"
      +}
  5. Addedv1.0.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered; the description still adds real behavior: 100-slide pagination with a trailing offset, z-order and nested groups for page, absence of geometry/styling in page mode, points vs EMU units, and locally-set-only styles. It stops short of describing error conditions or what happens with an invalid page_id, so it is not a full 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 one-line summary followed by a clean per-action breakdown, which is the right structure for a multi-mode tool. It is verbose in places and repeats some schema text (e.g. the action list shadowing the action parameter), costing a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Includes a per-action summary and directional hint to the sibling batch_update_presentation via the "raw" parameter. However, it omits key routing signals like expected response shape, pagination limits per mode, or error behavior, which are important for an agent invoking this complex tool.

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 each parameter is documented there, yet the description adds practical semantics: offset should come from the previous call's trailing note, after takes a slide ID or "start" and restricts to the master in use at that position, and targets accepts "notes" or a group ID. This goes beyond restating the schema, though some overlap remains.

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?

Opens with a specific verb and resource ("Read a deck") and then enumerates four concrete actions with what each returns ("page" gives element IDs and all text, "markup" gives compact JSON with geometry and styles). This is clearly distinguishable from siblings like batch_update_presentation or create_presentation.

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 explicit routing between modes: "start here for content" for page, "markup" for geometry and styles, and "layouts" only needed when the deck listing says there are more layouts than it shows. It also states conditional dependencies, e.g. page and markup require page_id, and offset comes from the previous call's note.

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