Revid

Generate media

generate_media

Generate standalone image or video media using the same prompt, quality, ratio, preset, duration, frame, reference, audio, and character options as the Revid media generator. The media is saved to the user's Revid media library. The call waits up to 40 seconds. A generation done by then returns status "ready" with each media's url. A longer one (ultra images often, videos usually: 1 to 10 minutes) returns status "processing" with mediaIds: call get_media_status with them until the status is ready or failed. Do not call generate_media again for the same request while it is processing: every call starts and charges a new generation. Requires an active Revid plan.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "generate_media"
  }
}

Input Schema

Name	Required	Description
`audio`	No	For videos, add audio to generated output, spoken lines included. Defaults to true; pass false for a silent clip.
`count`	No	Image count. Videos generate one item, matching the media generator UI.
`media`	No
`ratio`	No	Output ratio.
`video`	No
`preset`	No	Alias of generationPreset.
`prompt`	No	Media prompt. You can also use source.prompt or input.
`source`	No
`options`	No
`quality`	No	Image or video quality, same values as the media generator UI.
`voiceId`	No	Optional voice id for generated video audio processing.
`duration`	No	Video duration in seconds.
`lastFrame`	No	Optional video last-frame image URL.
`mediaType`	No	Media type to generate. Defaults to image.
`firstFrame`	No	Optional video first-frame image URL.
`inputAudios`	No	Alias of referenceAudios.
`inputImages`	No	Alias of referenceImages.
`inputVideos`	No	Alias of referenceVideos.
`characterIds`	No	Consistent character ids.
`improvePrompt`	No	Improve the image/video prompt before generation.
`referenceAudios`	No	Audio reference URLs for video generation.
`referenceImages`	No	Image reference URLs.
`referenceVideos`	No	Video reference URLs for video generation.
`generationPreset`	No	Optional Revid media generator preset value.
`selectedCharacters`	No	Alias of characterIds.

Output Schema

Name	Required	Description	Default
`ok`	Yes
`data`	No
`error`	No
`method`	Yes
`status`	Yes
`endpoint`	Yes
`retryAfterSeconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Beyond the annotations it discloses output destination (user's media library), a 40-second synchronous wait, the two possible status values and their payloads (url vs mediaIds), realistic timing for ultra images and videos, credit charging, and a plan requirement. The annotations already signal a non-idempotent, non-read-only, open-world operation, so this is strong additive context rather than a contradiction.

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-loaded with the purpose, then the sync/async behavior, the polling instruction, and the charging warning in a logical order, all in about five sentences. The opening list of ten option names is somewhat redundant with the schema and could be trimmed without losing information.

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 25-parameter, nested, non-idempotent generation tool with an output schema and annotations, the description supplies everything missing: cost model, wait behavior, status branches, follow-up tool, and entitlement prerequisite. An agent has enough to invoke it and handle both response shapes correctly.

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 84%, so the schema already documents most parameters and a baseline of 3 applies. The description only enumerates option categories (prompt, quality, ratio, preset, duration, frame, reference, audio, character) and says they mirror the Revid generator UI; it does not clarify the heavily duplicated aliasing (preset vs generationPreset, inputImages vs referenceImages, options.* duplicates), which is where added meaning would have helped most.

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 ("Generate standalone image or video media") and the word "standalone" implicitly separates it from project/episode-based generation siblings like render_video and create_episode. It also names get_media_status explicitly, so the agent can place this tool in the workflow without opening a 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 when-not ("Do not call generate_media again for the same request while it is processing"), the reason (each call starts and charges a new generation), and the correct alternative (poll get_media_status). It also states the precondition of an active Revid plan.

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

All Revid tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?