Skip to main content
Glama

Create a video

create_video
Destructive

Starts rendering a video and spends its credits (refunded if it fails). Returns at once with an id: poll get_generation until it is completed.

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": {
      "prompt": "<prompt>"
    },
    "name": "create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoQuality tier: quick (cheapest), great (best value, default), cinema (most realistic). Or give `model` instead.
imageNoOptional start image: base64 JPEG, PNG or WebP (a data: URL works), under 10 MB.
modelNoA model id from list_models, instead of a tier.
soundNoSound on or off, where the model has a switch. Quick always has sound.
promptYesWhat to make, in plain words. @handles use the person's saved characters.
durationNoSeconds, from the model's durations (list_models).
image_idNoOptional start image already sent to POST /v1/uploads.
resolutionNoe.g. "720p" or "1080p" for videos, "2K" for images. Defaults to the tier's.
max_creditsNoRefuse instead of spending more than this many credits.
aspect_ratioNoAspect ratio, e.g. "16:9", "9:16" (vertical, for Reels and TikTok) or "1:1".
photo_consentNoRequired with an image: true only if the person confirmed they have the right to use it and the people in it agree.
idempotency_keyNoRetrying with the same key never creates twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag destructive=true and non-idempotent, and the description adds genuinely new behavior: credits are spent up front, refunded on failure, and the call is asynchronous returning an id. It does not mention the idempotency_key escape hatch despite idempotentHint=false, which is the one notable gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the cost-and-destructive implication, then the async return contract. Nothing is wasted and the next action is stated last where it is most actionable.

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

Completeness4/5

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

For a 12-parameter mutation with no output schema, the definition covers cost, refund, and the return/polling contract that an agent most needs. It leaves out prerequisite details such as the upload flow behind image_id and when to consult estimate_cost, but the rich schema carries the rest.

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% and each of the 12 parameters, including tier, max_credits, and photo_consent, is documented in the schema itself. The description adds no parameter-level meaning, so the baseline 3 applies.

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?

"Starts rendering a video" gives a specific verb and resource, and the polling instruction cleanly separates it from get_generation. It does not distinguish itself from video-adjacent siblings such as create_film or create_ad, so the agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the follow-up workflow explicitly: the call returns an id at once and you must poll get_generation until completed. It gives no exclusions or guidance on when to prefer create_film/create_ad instead, but the primary usage context is unambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources