Skip to main content
Glama

Create Ugc Video

create_ugc_video
Destructive

[write, queued, priced] Create a UGC product video: a READY character presents an advertisement (worker_videos_ugc builds the script, voices, clips and timeline). video_ugc = {character_uuid, character_uuids?, advertisement_uuid?, ugc_prompt?, ugc_duration? 5-45s, ai?, scene_image?, scene_ai?, product_image?, product_note?, ugc_voice?, ugc_motion?, sfx?} (shape: EnumVideos.ugc_enums). ai = the script AI {provider: openai|claude|gemini|xai|llama, account_uuid, model?} (omitted: the local Seliee AI writes it; list_ai_accounts answers the UUIDs). scene_image = the start picture {url, path?, storages_account_uuid?} the clips start from; scene_ai {provider, account_uuid, model?} is the image account that redraws it with the characters in place of its people (list_images_ai_accounts); product_image {url, path?, storages_account_uuid?} rides on the video picture-in-picture. ugc_voice = {provider, account_uuid, voice?, model?, character_voices?} and ugc_motion = {provider, account_uuid, model?}: name the account by its UUID account_uuid (never the numeric id; list_voices_ai_accounts / list_motions_ai_accounts answer the UUIDs, models and voices), else ERR_INPUT__ACCOUNT_ID; elevenlabs also needs voice. video_render_target = {storages_account_id or storages_account_uuid, video_render_target_path?} is REQUIRED. Answers video_id and video_uuid; then render_video once the timeline is built.

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": {
      "video_title": "<video_title>",
      "video_ugc": "<video_ugc>",
      "video_render_target": "<video_render_target>"
    },
    "name": "create_ugc_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
video_ugcYes
video_titleYes
video_outputNo
video_keywordsNo
video_languageNo
video_descriptionNo
video_render_targetYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Goes beyond the annotations by tagging the call as [write, queued, priced], disclosing that work is queued asynchronously and costs credits, and by naming the exact failure mode ERR_INPUT_<PROVIDER>_ACCOUNT_ID with the fix (use account_uuid, not the numeric id). It still doesn't say whether a duplicate call creates a duplicate queued job or how to cancel, which matters for a non-idempotent, destructive-flagged write.

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

Conciseness3/5

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

Front-loaded with the action and the subject, and every clause is informational, but the body is a single dense run-on packed with brace notation and semicolons that is hard to parse on first read. A short structured breakdown of the ugc fields would preserve the content with better scanability.

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 7-param tool with nested free-form objects, no output schema and no annotation detail, it supplies the lifecycle (queue, then render_video), the returned identifiers (video_id, video_uuid) and provider-specific requirements such as elevenlabs needing voice. The main residual gap is the unexplained video_output/video_keywords/video_language/video_description parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage and opaque additionalProperties objects, the description carries nearly the whole burden and does it well: it expands video_ugc keys, ai, scene_image, scene_ai, product_image, ugc_voice and ugc_motion, and flags video_render_target as REQUIRED. It says nothing about video_output, video_keywords, video_language or video_description, leaving four top-level params undocumented in both places.

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 ("Create a UGC product video") plus the core mechanism ("a READY character presents an advertisement") and the backing worker (worker_videos_ugc). This clearly separates it from sibling video creators like create_video, create_film_video and create_promo_video, since 'READY character presents advertisement' is a distinct concept.

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?

Gives concrete workflow guidance: call render_video once the timeline is built, and points to list_ai_accounts / list_voices_ai_accounts / list_motions_ai_accounts for required UUIDs. It never names the alternative sibling tools (create_video, create_promo_video) or states when not to use this one, so it falls short of explicit alternatives.

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.