Skip to main content
Glama

Create Video

create_video
Destructive

[write] Create a video project (DRAFT). video_language is a language name such as english or turkish (a tag like en / tr is converted). video_source = raw source from (video_source_url, video_source_language, video_source_duration_max 5-600s, video_source_prompt brief, video_source_presenter = who comments: {mode: character, character_uuid} (an AI character from list_characters, shown picture-in-picture, the copy is written in its voice) or {mode: video, storages_account_id or storages_account_uuid, path, name, url} (a face explanation video from a storage account, played picture-in-picture over the edit with the source ducked under it)) - queues analysis + auto edit generation; video_output = render settings (default 1080x1920 mp4). Then call render_video. 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>"
    },
    "name": "create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
video_titleYes
video_outputNo
video_sourceNo
video_keywordsNo
video_languageNo
video_descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), it discloses that the tool creates a DRAFT, that supplying video_source triggers queued analysis and auto edit generation, that output defaults to 1080x1920 mp4, and that it returns video_id and video_uuid. That is substantive behavioral context an agent would not get from the annotations. It does not say whether the draft is deletable or how long analysis takes.

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-loads the action and the draft/render workflow, which is good, but the body is a single run-on sentence with deeply nested parentheses that is hard to parse. It also contains a truncated fragment ('raw source from ') that reads like a lost reference, hurting clarity.

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 six-parameter creation tool with no output schema, the description covers the hardest part (the nested video_source presenter modes) and the return identifiers well. It falls short on the three simpler parameters and offers no guidance on keyword or description usage, so an agent could still call it incompletely.

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 0%, so the description must carry the load: it explains video_language (accepts names like english/turkish or tags like en/tr), the duration bounds for video_source_duration_max (5-600s), and both presenter modes with their required keys. However, video_title, video_keywords, and video_description are never mentioned, leaving half the parameters undefined anywhere.

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?

States a specific verb and resource ('Create a video project (DRAFT)') and flags the draft state plus the follow-up render_video step. It does not differentiate itself from sibling creation tools like create_film_video, create_ugc_video, or create_promo_video, so an agent must infer which creator applies.

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

Usage Guidelines3/5

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

The description gives an in-workflow cue ('Then call render_video') and notes video_source queues analysis plus auto edit generation, which implies when this tool fits. It never says when to choose this over create_film_video, create_ugc_video, or create_promo_video, so selection among siblings remains ambiguous.

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.