Skip to main content
Glama

Submit Video Recreation Task

submit_video_recreation_task
Destructive

Starts one video recreation task using a source video and one or more reference images. For this task, pass task_source='hit_recreate' to get_task. May consume existing Fotor credits. Returns a task ID without waiting for completion; use get_task to check its status once. This tool does not poll for completion. Repeating the request may create another task and consume additional credits. Do not automatically retry when the submission outcome is uncertain. This tool does not purchase credits or initiate a checkout flow.

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_url": "<video_url>",
      "image_urls": "<image_urls>"
    },
    "name": "submit_video_recreation_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptNoOptional instructions describing the changes; omit to use the upstream workflow.
video_urlYesAccessible HTTPS URL of the source video to recreate.
image_urlsYesOrdered accessible HTTPS reference image URLs; supply at least one.
resolutionNoOutput video resolution.720p
prompt_switchNoUpstream prompt switch: on or off.on

Output Schema

NameRequiredDescriptionDefault
statusNoSubmission accepted; generation is not yet confirmed complete.submitted
task_idYesFotor task ID for get_task.
task_typeNoVideo recreation operation.hit_recreate
media_typeNoGenerated media category.video
task_sourceNoPass this task_source to get_task together with task_id.hit_recreate
credits_incrementNoActual credit consumption from deductionNum; null if unavailable. Not a charge on each query.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior3/5

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

Annotations already flag readOnly=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, and the description builds on that with credit consumption, an immediate task-ID return without waiting, and duplicate-task risk on repeat submission — real added context. The remaining gap is that it never says what the response object contains or what failure signals look like, so the behavioral picture is strong on risk but thin on outcomes.

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 first two sentences front-load what the tool does and how to continue, and each later sentence carries a distinct safety or billing constraint. It is somewhat long and the negative framing is repeated (no polling, no auto-retry, no credit purchase), which costs a little tightness without introducing noise.

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, asynchronous submission tool this covers everything an agent needs: required inputs, immediate task-ID return, credit impact, no internal polling, duplicate-submission risk, and no retry under uncertainty. With an output schema present and full parameter coverage, nothing material is left undocumented.

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 100%, so the schema already documents prompt, video_url, image_urls, resolution, and prompt_switch, and the description adds no syntax or format detail beyond restating that a source video and reference images are supplied. Its one genuinely additive parameter note — passing task_source='hit_recreate' — applies to get_task rather than this tool's own inputs, so baseline 3 is appropriate.

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?

The description gives a specific verb and resource ("Starts one video recreation task") and immediately pins down the payload shape — a source video plus one or more reference images — which is what separates it from the other submit_* video tools. It also names the downstream call (get_task with task_source='hit_recreate'), so an agent knows exactly which sibling continues the operation.

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?

It clearly routes follow-up work to get_task and forbids polling, auto-retry, and checkout initiation — concrete when/when-not guidance. What it lacks is an explicit statement of when to choose this submission tool over the sibling video variants (first-frame, multimodal, text-to-video); the distinction is left to the required parameters.

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.

Resources