Skip to main content
Glama

Generate a video from a topic

autoshort_generate_video
Idempotent

Turn a topic into a narrated short video, optionally using your own images for the first scenes. AutoShort writes the script, generates the voiceover, renders scenes, and returns a job to poll.

Instructions

Generate a video from a topic; AutoShort writes the script (to render a script you already agreed with the user, use autoshort_draft_video). Optional image_urls (public https links, up to 6) put the user's own pictures in the first scenes. Costs 65 credits (40 render + 25 ElevenLabs voice); art style does not change the price. Images do not change the price. A short balance is refused with 402 INSUFFICIENT_CREDITS. Rendering is asynchronous: poll autoshort_get_video every 20-30 seconds until status is COMPLETED or FAILED. If get_video returns blockedReason, stop polling and act on it (e.g. top up credits). ROUTING: this makes a narrated video of still images from a topic. If the user pasted a cinematic / video-model prompt, use autoshort_generate_motion_clip instead.

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": {
      "topic": "<topic>"
    },
    "name": "autoshort_generate_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
nicheNoOptional content niche; see autoshort_list_niches.
topicYesWhat the video is about: one named subject, one angle, one twist. Short topics still work. e.g. "Why airplane windows have a tiny hole in them".
qualityNoOutput resolution. Omit for the plan's resolution; asking for more than the plan renders returns 403 QUALITY_NOT_IN_PLAN.
artStyleNoOptional art style; default AUTOSHORTS.
durationNoTarget length in seconds (default 30). 15/30/60/90 = multi-scene faceless video; 5 and 8 make a very short video on the same pipeline and price.
languageNoOptional BCP-47 code (e.g. "en", "vi"). Defaults to "auto".
image_urlsNoOptional. The user's OWN images to use as the first scenes: image 1 = scene 1, image 2 = scene 2, and so on; the remaining scenes are generated as usual. https URLs only, up to 6 per call, JPEG/PNG/WebP, each at most 10 MB and 25 megapixels; at most 30 images per hour per account. Animated WebP uses its first frame; GIF and SVG are rejected. AutoShort downloads each image once, strips EXIF/GPS, re-encodes it and serves it from its own domain (your URL is never linked into the video). Fast (FFMPEG) multi-scene videos only. The answer states how many images were used and for which scenes; more images than scenes is refused, never silently dropped. Only send images the user owns or may use; each is shown as a still with a slow zoom and is never animated or used to generate a person.
idempotencyKeyNoRetry-safe: a repeat with the same key returns the first answer (replayed: true) and creates nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing the concrete cost breakdown (65 credits = 40 render + 25 ElevenLabs voice), that art style and images do not change price, the exact failure mode (402 INSUFFICIENT_CREDITS), and the asynchronous lifecycle with polling cadence. The idempotencyKey replay behavior ("replayed: true") is consistent with idempotentHint=true, and blockedReason handling tells the agent how to recover rather than just that a failure exists.

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 purpose and the sibling exclusions before cost and async mechanics, and nearly every clause carries operational information. It is dense with semicolons and parentheticals (the routing block and blockedReason aside), which makes it slightly crowded but not padded.

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 costly, asynchronous, mutating generation tool with no output schema, the definition covers pricing, refusal codes, plan-based quality rejection, polling loop, abort condition, and even what the response reports (images used and for which scenes). Nothing an agent needs to invoke it safely and follow up correctly appears to be missing.

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 coverage is 100% and the image_urls/quality/duration descriptions in the schema are already exhaustive, so the description's restatement ("public https links, up to 6") adds little. It does add one genuinely new fact — that art style and image count do not affect price — but that is cost behavior rather than parameter meaning, so the baseline 3 holds.

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+resource ("Generate a video from a topic") and immediately scopes it against two named siblings: autoshort_draft_video for a pre-agreed script and autoshort_generate_motion_clip for cinematic/video-model prompts. The ROUTING line explicitly defines this as a narrated still-image video, so an agent can discriminate it from the motion-clip and draft tools without opening any schema.

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 when-to-use and when-not-to-use conditions with named alternatives ("to render a script you already agreed with the user, use autoshort_draft_video"; "if the user pasted a cinematic / video-model prompt, use autoshort_generate_motion_clip instead"). It also supplies the follow-up procedure (poll autoshort_get_video every 20-30 seconds until COMPLETED/FAILED) and a stop condition for blockedReason.

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