Live Card

Render a Live Photo card

render_live_card

Use this when the user wants an Apple Live Photo, a short animated card, or an MP4 or GIF from a design you can draw in HTML. Pass cover_html (the still) and motion_html (the animation). Both must be self-contained: inline SVG, inline CSS and data: URLs only. A remote image, font, script or style sheet is refused with external_url. Optional width and height (even, default 1080 by 1440, at most 1080 by 1440), duration_ms (500 to 3000, default 3000), fps (15 or 30, default 15) and cover_ms (the video time the still is paired to, default 0). CSS animations and requestAnimationFrame are sampled on a virtual clock from 0 to duration_ms. Returns status queued, a job_id, and a message telling you to call live_card_status. It does not return the files itself. It cannot fetch a URL, import into Photos, or run longer than 3 seconds.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "cover_html": "<p>Profile: Launch</p>",
      "motion_html": "<style>@keyframes fade{from{opacity:0}to{opacity:1}}</style><div style=\"animation:fade 3s linear\">Launch</div>"
    },
    "name": "render_live_card"
  }
}

Input Schema

Name	Required	Description
`fps`	No	Frames per second. Default 15.
`width`	No	Even pixel width. Default 1080.
`height`	No	Even pixel height. Default 1440.
`cover_ms`	No	Time in the video the still is paired to. Default 0. Must be a whole frame and less than duration_ms.
`cover_html`	Yes	Self-contained HTML for the still cover. Inline SVG, CSS and data: URLs only.
`duration_ms`	No	Length in milliseconds, 500 to 3000, a whole number of frames at fps. Default 3000.
`motion_html`	Yes	Self-contained HTML for the animation. CSS animations and requestAnimationFrame follow a virtual clock from 0 to duration_ms.

Output Schema

Name	Required	Description	Default
`as_of`	Yes
`job_id`	Yes
`limits`	No
`source`	Yes
`status`	Yes
`message`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026

addedInput schema / examples

Added value: +[
+  {
+    "cover_html": "<p>Profile: Launch</p>",
+    "motion_html": "<style>@keyframes fade{from{opacity:0}to{opacity:1}}</style><div style=\"animation:fade 3s linear\">Launch</div>"
+  }
+]

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 3, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare the generic safety profile (readOnly=false, destructive=false, openWorld=false); the description carries the real behavioral load: which inputs are refused with external_url, that animations are sampled on a virtual clock from 0 to duration_ms, and that no files are returned in this call. That is exactly the beyond-schema context an agent needs to avoid a failed invocation.

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 with the trigger sentence, then constraints, then return behavior -- a sensible order. It is long and duplicates a few schema facts (defaults, 1080x1440 cap, 3-second limit) that could have been left to the schema.

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

Completeness5/5

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

For a 7-parameter job-submitting tool with an output schema, everything an agent needs is present: input format requirements, refusal mode, dark-room constraints, and the handoff to live_card_status. Return value details can be omitted precisely because the output schema exists.

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 ranges, defaults and the enum for fps. The description restates those defaults and adds little new parameter meaning beyond reinforcing the self-containment rule, so the baseline 3 is appropriate.

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?

States a specific verb and artifact set: renders an Apple Live Photo / animated card / MP4 or GIF from HTML the caller supplies. The opening 'Use this when the user wants...' names concrete user intents, which separates it cleanly from live_card_status and the unrelated feedback/index siblings.

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 triggers ('Apple Live Photo, a short animated card, or an MP4 or GIF') plus explicit exclusions ('cannot fetch a URL, import into Photos, or run longer than 3 seconds'). It also routes the agent forward, telling it the result is a job_id and that it must call live_card_status, so the alternative is named rather than implied.

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

All Live Card tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.