Skip to main content
Glama

Add a web video

add_web_video

Places a YouTube, Vimeo, Loom, or direct video link on a presentation slide with title and poster image, then plays it in GlideDeck and exported HTML.

Instructions

Places a YouTube, Vimeo or Loom video (or a direct link to a video file) on a slide, with its title and poster image. It plays in GlideDeck and in the export_html web page (in the site's own player). Slide units: 1600 × 900, origin at the center.

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": {
      "path": "<path>",
      "url": "<url>"
    },
    "name": "add_web_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
urlYesLink to the video, e.g. https://www.youtube.com/watch?v=…
pathYesThe GlideDeck project file (.glide.json). Absolute, or relative to the server's folder; `.glide.json` is added when there is no extension.
stepNo
widthNo
autoplayNoStart playing when its slide is reached in the show.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations only declare readOnlyHint=false and openWorldHint=false, so the description must carry the rest, and it does add real behavior: the video plays both inside GlideDeck and in the export_html page using the site's own player, and a title and poster image are attached automatically. It does not say that placing the element mutates the .glide.json project file, whether title/poster retrieval is a network fetch at call time (in mild tension with openWorldHint=false), or what happens on an unsupported or dead link.

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?

Three short sentences, front-loaded with what gets created and where it will render, then the unit-system caveat. Every sentence adds information and nothing is repeated from the schema. Minor cost: the coordinate note could be folded more tightly into the placement sentence.

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?

For a 7-parameter mutation tool with no output schema, the description covers purpose, rendering targets and coordinate system, which is the core of what an agent needs. Gaps remain around the undocumented `step` parameter, prerequisites on the target file/slide, and behavior on invalid URLs, so it is adequate but not complete.

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?

Coverage is only 43%, so the description needs to compensate, and it does for geometry: 'Slide units: 1600 × 900, origin at the center' gives the units and coordinate frame that x, y and width (default 1000) otherwise lack. However, `step` is documented nowhere in the schema or the description, and nothing explains how width interacts with the video's aspect ratio or what a fractional position does.

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?

A concrete verb+resource: it 'places a YouTube, Vimeo or Loom video (or a direct link to a video file) on a slide.' Enumerating the supported providers and the fallback (direct file link) makes the scope unambiguous, and 'on a slide' naturally distinguishes it from add_image or add_text. It stops short of naming a sibling explicitly, so a 4 rather than a 5.

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?

Usage is only implied: an agent can infer 'use this to embed a video rather than an image or text.' There is no explicit statement of when to prefer add_image with a poster, no prerequisite about the slide/project having to already exist, and no exclusion of unsupported URLs. Context is clear but a good chunk is left to inference.

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