Skip to main content
Glama
Sign In

RYLA

by ai.ryla
OverviewDiscussionsAdmin

ryla_generate_video

Generate a video from an existing character image (image-to-video, Wan 3.0). Character must already exist; use ryla_list_characters to find a characterId. By default the newest completed image of the character is animated; pass sourceImageId (imageIds from ryla_account_gallery_list) to pick one. Priced per second and resolution (720p = 240 credits/s, 480p 120, 1080p 470; unrestricted x2). Returns a jobId; poll with ryla_generation_status.

Input Schema

NameRequiredDescriptionDefault
nsfwNoEnable unrestricted fan content generation
promptNoOptional prompt/description for the motion
durationNoVideo duration in whole seconds, 2 to 30
requestIdNoIdempotency key: the same id returns the same job and never charges twice. Generated when omitted.
wantAudioNoGenerate sound with the video
resolutionNoOutput resolution (drives the price)720p
aspectRatioNoVideo aspect ratio
characterIdYesCharacter UUID to generate video for
sourceImageIdNoImage UUID to animate (default: newest completed image)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changed
    • changedInput schema / properties / duration / description
      Previous value: -"Video duration in seconds"New value: +"Video duration in whole seconds, 2 to 30"
    • removedInput schema / properties / duration / enum
      Removed value: -[
-  5,
-  10
-]
    • addedInput schema / properties / duration / maximum
      Added value: +30
    • addedInput schema / properties / duration / minimum
      Added value: +2
    • changedInput schema / properties / duration / type
      Previous value: -"number"New value: +"integer"
    • removedInput schema / properties / fps
      Removed value: -{
-  "description": "Frames per second (default 24)",
-  "enum": [
-    24,
-    30
-  ],
-  "type": "number"
-}
    • changedInput schema / properties / prompt / description
      Previous value: -"Optional prompt/description for the video"New value: +"Optional prompt/description for the motion"
    • removedInput schema / properties / realismStyle
      Removed value: -{
-  "description": "Apply photorealism post-processing",
-  "type": "boolean"
-}
    • addedInput schema / properties / requestId
      Added value: +{
+  "description": "Idempotency key: the same id returns the same job and never charges twice. Generated when omitted.",
+  "format": "uuid",
+  "type": "string"
+}
    • addedInput schema / properties / resolution
      Added value: +{
+  "default": "720p",
+  "description": "Output resolution (drives the price)",
+  "enum": [
+    "480p",
+    "720p",
+    "1080p"
+  ],
+  "type": "string"
+}
    • removedInput schema / properties / seed
      Removed value: -{
-  "description": "Optional seed for reproducibility",
-  "type": "integer"
-}
    • addedInput schema / properties / sourceImageId
      Added value: +{
+  "description": "Image UUID to animate (default: newest completed image)",
+  "format": "uuid",
+  "type": "string"
+}
    • removedInput schema / properties / useLora
      Removed value: -{
-  "description": "Use character LoRA for face consistency (default true)",
-  "type": "boolean"
-}
    • addedInput schema / properties / wantAudio
      Added value: +{
+  "description": "Generate sound with the video",
+  "type": "boolean"
+}
    • changedInput schema / required
      Previous value: -[
-  "characterId",
-  "aspectRatio"
-]New value: +[
+  "characterId"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / duration / default
      Previous value: -4New value: +5
    • changedInput schema / properties / duration / enum
      Previous value: -[
-  2,
-  4,
-  5,
-  6,
-  8
-]New value: +[
+  5,
+  10
+]
  3. First observed

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the async job model (returns a jobId), the default image-selection behavior, and per-second/per-resolution pricing (720p=240, 480p=120, 1080p=470, unrestricted x2). It stops short of failure modes, rate limits, or what happens on insufficient credits, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what the tool does, then prerequisites, defaults, cost, and follow-up. Every sentence is load-bearing — the pricing list and the polling pointer are actionable rather than filler.

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 9-parameter async generation tool with no output schema and no annotations, the description supplies the missing context: cost model, default behavior, returned jobId, and the polling sibling. An agent has everything needed to invoke it correctly and handle the result.

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 100%, so the baseline is 3; the description adds real value by mapping resolution values to credit cost and explaining the default sourceImageId resolution path. It does not add meaning to prompt, wantAudio, aspectRatio, or nsfw beyond the schema text.

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 a video from an existing character image'), names the underlying model (image-to-video, Wan 3.0), and makes the prerequisite explicit ('Character must already exist'). An agent can tell this apart from sibling generators like generate_avatar_video and generate_video_swap without opening any 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 explicit routing: use ryla_list_characters to get a characterId, pass sourceImageId (from ryla_account_gallery_list) to pick an image, poll with ryla_generation_status. It also states the default behavior when sourceImageId is omitted, so there is no ambiguity about the alternative.

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

All RYLA toolsInspect
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