NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Google Slides connects to a Nagent workspace with OAuth sign-in. Once it is connected, agents can call 8 Google Slides actions, such as "Create Google Slides Presentation", "Create Slides from Markdown" and "Get Page Thumbnail v2". It also has 1 trigger, "New Slide Added", which can start agent work when that Google Slides event happens. Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Each Google Slidestrigger shows its configuration parameters and the payload your agent receives. A trigger fire is checked against the agent's level and logged, the same as work a person asked for.
GOOGLESLIDES_SLIDE_ADDED_TRIGGERFires when a new slide is added to a Google Slides presentation.
Configuration
Periodic Interval to Check for Updates & Send a Trigger in Minutes
The ID of the presentation to monitor for new slides
Payload
Type of slide event
The slide object that was added
Every operation an agent can call against Google Slides, with input parameters and output schema.
GOOGLESLIDES_CREATE_PRESENTATIONTool to create a blank Google Slides presentation. Use when you need to initialize a new presentation with a specific title, locale, or page size.
Input parameters
The title of the presentation. If omitted, the API uses a default title.
The locale of the presentation, as an IETF BCP 47 language tag (e.g., 'en-US', 'fr-FR', 'ja-JP'). If omitted, the API uses a default locale.
The size of a page in the presentation.
The ID to use for the new presentation. If provided, it is used as the ID of the new presentation. Otherwise, a new ID is automatically generated. Must be a valid Google Drive/Slides ID format (long alphanumeric string). Note: Human-readable IDs (e.g., 'my-presentation') are not valid and will cause API errors. Only provide this if you have a valid Google Drive/Slides ID format; otherwise omit to let the API generate one.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLESLIDES_CREATE_SLIDES_MARKDOWNCreates a new Google Slides presentation from Markdown text. Automatically splits content into slides using '---' separators and applies appropriate templates based on content structure.
Input parameters
The title for the new Google Slides presentation.
The content for the slides, formatted as Markdown. THEME SELECTION: Add `Theme: <name>` at the start of your markdown. Available themes: default, corporate_blue, modern_dark, professional_gray, creative_purple, warm_orange, forest_green, minimal_beige. SLIDE SEPARATION: Use ' --- ' (on its own line) to separate slides. Each slide auto-detects its type. SLIDE TYPES: 1. Title Slide (first slide): `# Title Subtitle text` 2. Bullet Slides: Use `-`, `*`, or bullet characters for bullets 3. Table Slides: Standard markdown tables 4. Quote Slides: `> Quote text` 5. Text Slides: Regular paragraphs 6. Image Slides: `!\[description\](URL)` 7. Two-Column Slides: Use `\\|\\|\\|` on its own line to split left/right IMAGE REQUIREMENTS: Images must be publicly accessible PNG/JPEG/GIF under 50MB. No auth-requiring URLs. FORMATTING: Use `**text**` for bold. Emojis supported. Line breaks preserved.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLESLIDES_GET_PAGE_THUMBNAIL2Tool to generate a thumbnail of the latest version of a specified page. Use when you need a preview image URL for a slide page. This request counts as an expensive read request for quota purposes.
Input parameters
The object ID of the page whose thumbnail to retrieve.
The ID of the presentation to retrieve.
The optional mime type of the thumbnail image. Defaults to PNG if not specified.
The optional thumbnail image size. LARGE = 1600px, MEDIUM = 800px, SMALL = 200px. Defaults to LARGE if not specified.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLESLIDES_PRESENTATIONS_BATCH_UPDATEUpdate Google Slides presentations using markdown content or raw API text. Supports professional themes, auto-formatting, and multiple slide types (title, bullet, table, quote, image, two-column).
Input parameters
List of update requests, each a dict with one of these valid Slides API request types: **Common requests:** createSlide, createShape, createTable, createImage, insertText, updateTextStyle, updateShapeProperties, updatePageProperties, updateParagraphStyle, deleteObject, updateTableCellProperties, updateTableColumnProperties, replaceAllText **IMPORTANT:** To update slide backgrounds, use `updatePageProperties` (NOT `updateSlideProperties`). The field `pageBackgroundFill` exists in PageProperties, not SlideProperties. Required if markdown_text is not provided.
Options that control how write requests are executed.
Markdown content to add as new slides to an existing presentation. Separate slides with '\\n---\\n'. Each slide auto-detects its type from content. Slide types: title ('# Title\\nSubtitle'), bullets ('-'/'+'/'*'), tables (markdown tables), quotes ('> text'), images ('!\[alt\](URL)'), two-column ('\\|\\|\\|' separator), plain text. Add 'Theme: <name>' as the first line to apply a theme. Available themes: default, corporate_blue, modern_dark, professional_gray, creative_purple, warm_orange, forest_green, minimal_beige. Font sizes auto-scale based on content length (28pt down to 8pt). Supports **bold**, emoji, and auto-centering of tables. Images must be publicly accessible URLs (PNG/JPEG/GIF, <50MB).
The ID of the presentation to apply the updates to.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLESLIDES_PRESENTATIONS_COPY_FROM_TEMPLATETool to create a new Google Slides presentation by duplicating an existing template deck via Drive file copy. Use when you need to preserve themes, masters, and layouts exactly as they appear in the template. After copying, use GOOGLESLIDES_PRESENTATIONS_BATCH_UPDATE to replace placeholder text or images.
Input parameters
The name/title for the copied presentation. If omitted, a default name like 'Copy of \[original\]' is used.
The ID of the destination folder in Google Drive. If provided, the copied presentation will be placed in this folder. If omitted, the copy is placed in the user's root folder.
The Drive file ID of the Slides template to copy. This is the presentationId of the existing deck you want to duplicate.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLESLIDES_PRESENTATIONS_GETTool to retrieve the latest version of a presentation. Use after obtaining the presentation ID.
Input parameters
Comma-separated selector specifying which fields to include in a partial response. Nested fields use parentheses that must be properly balanced. Top-level fields: presentationId, title, locale, revisionId, pageSize, slides, masters, layouts, notesMaster. For slides/masters/layouts, valid Page fields: objectId, pageType, pageElements, pageProperties, revisionId. For pageElements, valid fields: objectId, size, transform, title, description, shape, image, video, line, table, wordArt, elementGroup, sheetsChart, speakerSpotlight. For shape, valid fields: shapeType, text, shapeProperties, placeholder. Note: 'autofit' is under shapeProperties, not directly under shape. Use shape(shapeProperties(autofit)), not shape(autofit). Examples: 'presentationId,title', 'slides(objectId,pageElements(objectId,size))', 'slides(objectId,pageElements(objectId,shape(shapeType,text,shapeProperties(autofit))))'
The ID of the presentation to retrieve. Either presentation_id or presentation_name must be provided.
The name of the presentation to search for and retrieve. If provided, the action will search Google Drive for a presentation with this name. Either presentation_id or presentation_name must be provided.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLESLIDES_PRESENTATIONS_PAGES_GETTool to get the latest version of a specific page in a presentation. Use when you need to inspect slide, layout, master, or notes page details.
Input parameters
The object ID of the page to retrieve.
The ID of the presentation from which to fetch the page.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLESLIDES_PRESENTATIONS_PAGES_GET_THUMBNAILDEPRECATED: Use GOOGLESLIDES_GET_PAGE_THUMBNAIL2 instead. Tool to generate and return a thumbnail image URL for a specific page. Use when you need a quick preview of a slide page after loading it.
Input parameters
The object ID of the page whose thumbnail to retrieve.
The ID of the presentation containing the page.
Optional thumbnail image MIME type. Currently only 'PNG' is supported by the API. Defaults to 'PNG' if omitted.
Optional thumbnail size. One of 'LARGE', 'MEDIUM', 'SMALL', or 'THUMBNAIL_SIZE_UNSPECIFIED'. Defaults to 'LARGE' if omitted.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 8 Google Slides actions on Nagent, including "Create Google Slides Presentation", "Create Slides from Markdown" and "Get Page Thumbnail v2". Create Google Slides Presentation: Create a blank Google Slides presentation. Each action is listed on this page with its input parameters and its output.
Google Slides connects with OAuth sign-in, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Yes. Google Slides has 1 trigger on Nagent, "New Slide Added", a poll trigger. It needs presentation_id, and takes an optional interval. A trigger fire is checked against the agent's level and logged, the same as work a person asked for.
It also takes 4 optional inputs: title, locale, pageSize and presentationId. It returns data, error and successful.