Skip to main content
Glama

generate_video

Creates billed AI video generation jobs from prompts, enforces budgets, prevents duplicate charges, and saves outputs automatically. Returns a job ID to track status.

Instructions

영상 생성 작업을 만든다. 과금된다. 사용자가 영상 생성을 요청했을 때만 부른다.

    기본값: config.toml 의 defaults (seedance-2.5 / Replicate, 480p, 5초, 16:9).
    모델마다 허용 해상도·길이·화면 비율과 가격이 다르다. 다른 모델을 쓰기 전에 list_models 로 확인한다
    (예: veo 는 4·6·8초, wan 은 5·10초, hailuo 는 6·10초만). 지정하지 않으면 모델에 맞는 가장 싼 값을 고른다.
    자동 길이는 허용하지 않는다. 일일·월간 예산을 넘으면 거부한다.
    job_id 를 반환한다. 완료되면 서버가 출력 폴더에 자동 저장하며, get_video_status 로 확인한다.
    오류가 "다시 보내지 마세요"라고 하면 같은 요청을 반복하지 않는다.
    같은 요청(프롬프트·모델·해상도·길이·비율)이 최근에 이미 접수됐으면 새 작업을 만들지 않고 기존 job_id 를
    duplicate=true 로 돌려준다 (과금 없음). request_id 를 주면 그 값으로도 중복을 잡는다.
    사용자가 같은 영상을 하나 더 원할 때만 force=true 를 쓴다.
    1차 제공처가 요청을 확정 거부하면 대체 모델로 만들고 failover_from 에 원래 모델을 적는다.
    예상 비용이 설정 임계값 이상이면 서버가 사용자에게 직접 확인을 요청할 수 있다.
    

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": "generate_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNo
modelNo
promptYes
request_idNo
resolutionNo
aspect_ratioNo
duration_secNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations: billing is charged, daily/monthly budget caps cause rejection, cost above a threshold triggers user confirmation, provider failover is recorded in failover_from, and auto duration is forbidden. The dedupe rule (recent identical request returns existing job_id with duplicate=true, no charge) sits in mild tension with idempotentHint=false, but it is bypassable via force=true so it is not a true contradiction. Only the actual failure modes of the underlying provider are left unexplained.

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?

Front-loads the most important fact (billing) in bold, then layers defaults, constraints, return value and edge cases in a reading order that matches real use. It is long, and the inline per-model duration examples add bulk, but each line maps to a decision the agent must make.

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

Completeness5/5

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

For a costly, non-idempotent, open-world generation tool with 7 parameters and no schema descriptions, this covers defaults, pricing variance, budget rejection, dedupe, force-bypass, failover, confidence-threshold confirmation and error handling. Return behavior is summarized (job_id) even though an output schema exists, and the follow-up tool is named.

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?

Schema coverage is 0%, so the description must compensate, and it largely does: force, request_id, model, resolution, duration and aspect ratio all get meaning (defaults, model-dependent constraints, cheapest-fit selection, dedupe key). The prompt parameter itself is left implicit – no guidance on content, limits, or specificity expected. The mapping from prose to exact parameter names is also slightly indirect for resolution/duration/aspect_ratio.

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+resource combination ('영상 생성 작업을 만든다') and immediately distinguishes itself from siblings: listing models goes to list_models, completion polling goes to get_video_status. The agent can tell it apart from estimate_video/preview_video without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit gate ('사용자가 영상 생성을 요청했을 때만 부른다'), an explicit alternative for model choice (list_models, with per-model duration examples), and an explicit condition for the force parameter ('사용자가 같은 영상을 하나 더 원할 때만'). It also warns against resending after a terminal error.

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