Skip to main content
Glama

Create Film Video

create_film_video
Destructive

[write, queued, priced] Create a film from characters and a scenario (same pipeline as the UGC video). video_ugc = {character_uuid (the READY character that opens the film), ugc_scenario (story/script, up to 6000 chars), ugc_duration? 30-120s (60 default), ai? (the script AI {provider, account_uuid, model?}), scene_image? (the start picture {url, path?, storages_account_uuid?}), ugc_voice? / ugc_motion? (accounts by account_uuid, a UUID from list_voices_ai_accounts / list_motions_ai_accounts, never the numeric id), sfx?, scene_ai?, storyboard? (1-12 scenes from plan_film_storyboard, each with its picture's public https image_url; replaces the scenario text as the script and the pictures open the clips; needs dialogue), storyboard_ai? {provider, account_uuid, model?}} (shape: EnumVideos.films_enums, storyboard_scene_enums). video_render_target is REQUIRED. Answers video_id and video_uuid.

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_film_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

A4/5.0
Behavior4/5

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

Annotations already declare it is a non-read-only, non-idempotent, destructive-classed write; the description adds the important behavior that it is queued and priced (consumes credits), and that it returns video_id and video_uuid. It stops short of describing cost magnitude, queue latency, or how to poll/retry, but adds meaningful context beyond the annotation set.

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?

The verb and operation tags are front-loaded, and nearly every clause carries information about a required input or prerequisite. It is dense and parenthesis-heavy, bordering on a wall of text, but there is little redundancy to cut.

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

Completeness3/5

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

For a high-complexity, nested-payload, paid generation tool with no output schema, the description covers the ugc payload well and names the two returned IDs. It leaves out the shape of video_render_target (a required parameter), the meaning of the four optional metadata parameters, and any guidance on timeouts or polling.

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 0% and the nested objects are untyped (additionalProperties: true), so the description carries real weight — it fully enumerates video_ugc fields (character_uuid, ugc_scenario with a 6000-char cap, ugc_duration 30-120s default 60, ai, scene_image, voices/motions, storyboard, storyboard_ai) and flags video_render_target as REQUIRED. However video_title, video_output, video_keywords, video_language and video_description are never explained, so half the parameters remain opaque.

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 film from characters and a scenario') and immediately situates it against the sibling pipeline ('same pipeline as the UGC video'), which separates it from create_ugc_video, create_video and create_promo_video. The bracketed '[write, queued, priced]' tag adds operation class up front.

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?

Provides real routing guidance for prerequisites: character_uuid must be a READY character, storyboard must come from plan_film_storyboard (1-12 scenes), and voice/motion accounts must be UUIDs from list_voices_ai_accounts / list_motions_ai_accounts ('never the numeric id'). It does not state when to prefer this over create_ugc_video or create_video, which is the main gap.

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.