Creatify Ad Agent

composer_generate_clip

Generates one clip (5-15 s) into the project as an async task: Boreal H3 for r2v/t2v/i2v, Aurora 2.0 for a2v. Returns task_id and the credit cost; the finished task's result includes the clip's CDN URL.

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": {
      "project_id": "<project_id>",
      "mode": "<mode>",
      "prompt": "<prompt>",
      "out": "<out>"
    },
    "name": "composer_generate_clip"
  }
}

Input Schema

Name	Required	Description	Default
`out`	Yes	Path relative to the project, e.g. gen/shot1.mp4.
`mode`	Yes	r2v: conditioned on reference images/videos. i2v: animates a given first frame. t2v: text only. These three render on Boreal H3. a2v: lip-syncs a speaker frame to an audio track on Aurora 2.0.
`seed`	No	Random seed. An identical request (same seed) within 10 minutes returns the existing task without a new charge.
`audio`	No	a2v dialogue track.
`image`	No	i2v/a2v first frame.
`audios`	No	r2v reference audio (voice/sound), project paths.
`images`	No	r2v reference images (<=9), project paths.
`prompt`	Yes	Shot description, including camera and subject motion.
`videos`	No	r2v reference videos, project paths.
`duration`	No
`last_image`	No	i2v end frame.
`project_id`	Yes	project_id from composer_project_create.
`resolution`	No	Output tier for r2v/t2v/i2v; 768P costs about a third of 1088P. a2v always renders at 720p.	1088P
`aspect_ratio`	No	Output aspect. Defaults to the project's aspect for r2v/t2v, and to the keyframe's own aspect for i2v/a2v.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 22, 2026

changedInput schema / properties / mode / description

Previous value: -"r2v: conditioned on reference images/videos. i2v: animates a given first frame. a2v: lip-syncs a speaker frame to an audio track. t2v: text only."New value: +"r2v: conditioned on reference images/videos. i2v: animates a given first frame. t2v: text only. These three render on Boreal H3. a2v: lip-syncs a speaker frame to an audio track on Aurora 2.0."

First observedOct 19, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) the description discloses the async task model, credit consumption, and the fact that the CDN URL arrives only in the finished task's result. It does not say whether credits are spent on failure or how long tasks may take.

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 tight clauses: what it does first, then what it returns. No padding, no restated parameter list, and the async/return information is front-loaded where an agent will read it.

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 14-parameter mutation tool with no output schema, the description supplies the essential missing piece, the return shape (task_id, credit cost, eventual CDN URL). It stops short of describing the follow-up polling step or partial-failure behavior, which would round it out.

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 93%, so nearly every parameter is already documented, and the mode-to-model mapping in the description largely duplicates the schema's own 'mode' description. It adds only the 5-15 s duration bound, so the baseline 3 applies.

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 resource ('Generates one clip (5-15 s) into the project as an async task'), names the models used per mode, and names the return artifacts. An agent can separate this from composer_generate_music or composer_voice_line without reading the schema.

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?

The mode-to-model routing (Boreal H3 for r2v/t2v/i2v, Aurora 2.0 for a2v) gives clear usage context and the mention of the finished task implies the polling path. However, it never explicitly says when to prefer a sibling such as composer_generate_music or how to chain to composer_task_status.

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

All Creatify Ad Agent 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.

Resources

Need Help?