AnimGen

Generate source video

generate_video

DestructiveIdempotent

Start a paid video-only task with approved quote_id or max_credits. Save the task ID, poll get_video_generation, then retain the video asset ID for previews and exports.

Input Schema

Name	Required	Description
`request`	Yes
`quote_id`	No
`max_credits`	No	Approved per-operation credit cap.
`idempotency_key`	Yes	Persist and reuse for this logical video generation.

Output Schema

Name	Required	Description
`id`	Yes	Persist this task ID immediately after create; poll it instead of creating again.
`error`	No	Task failure details, independently of any usable outputs.
`stage`	No	Current pipeline stage when available.
`object`	Yes	Public task resource type.
`status`	Yes	succeeded, failed, and cancelled are terminal; cancelling is not terminal.
`credits`	Yes	Quoted, reserved, and charged credit states.
`outputs`	No	Available assets, including partial outputs on failed/cancelled tasks. Always inspect them at a terminal state.
`metadata`	No	Caller-provided metadata.
`progress`	Yes	Fraction from 0 to 1, not a completion-time estimate.
`created_at`	Yes	UTC acceptance timestamp.
`started_at`	No	UTC production start when known.
`finished_at`	No	UTC terminal timestamp when known.
`resolved_export`	No	Persisted FPS sampling summary shared with the quote and manifest; null for legacy tasks.
`normalized_input`	No	Normalized public input; may contain private prompts or image references. Do not log wholesale.
`cancellation_reason`	No	Stable reason when cancellation is unavailable: TASK_TERMINAL, CANCELLATION_PENDING, CANCELLATION_NOT_CONFIRMED, or GENERATION_ALREADY_SUBMITTED.
`cancellation_allowed`	No	Whether a cancellation request can currently be accepted. Remote cancellation still needs confirmation.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 31, 2026

addedOutput schema / properties / cancellation_allowed

Added value: +{
+  "default": false,
+  "description": "Whether a cancellation request can currently be accepted. Remote cancellation still needs confirmation.",
+  "title": "Cancellation Allowed",
+  "type": "boolean",
+  "x-description-zh": "当前是否允许受理取消请求；远端取消仍须确认。"
+}

addedOutput schema / properties / cancellation_reason

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Stable reason when cancellation is unavailable: TASK_TERMINAL, CANCELLATION_PENDING, CANCELLATION_NOT_CONFIRMED, or GENERATION_ALREADY_SUBMITTED.",
+  "title": "Cancellation Reason",
+  "x-description-zh": "不可取消的稳定原因：TASK_TERMINAL、CANCELLATION_PENDING、CANCELLATION_NOT_CONFIRMED 或 GENERATION_ALREADY_SUBMITTED。"
+}

AddedSep 15, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already flag openWorld, idempotent, destructive, non-read-only, but the description adds what they cannot: the operation is PAID/credit-consuming, requires a pre-approved quote or cap, and is asynchronous. It does not explain failure/insufficient-credit behavior or what the destructive flag actually destroys, keeping it below 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?

Two sentences, both load-bearing: the first covers cost/gating, the second covers the async lifecycle. The critical cost precondition is front-loaded with zero filler.

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

Completeness4/5

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

An output schema exists, so return values need not be explained, and the description still supplies the lifecycle glue (task ID → get_video_generation → asset ID) that an agent needs to chain calls. What is missing is model-capability requirements (e.g. first_frame support) and the polling/retry contract for a long-running openWorld task.

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 50%, and the description clarifies the role of quote_id and max_credits ('approved', 'or') but leaves ambiguous whether both can be supplied and what happens if neither is. idempotency_key is left entirely to the schema, and the nested request object is not described beyond the schema's own rich field docs.

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 ('Start a paid video-only task') and the billing inputs that gate it ('approved quote_id or max_credits'). The 'video-only' qualifier implicitly separates it from generate_animation, though it never names that sibling directly.

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?

Gives the prerequisite (approved quote_id or max_credits) and outlines the follow-up flow (poll get_video_generation, retain asset ID). However it does not say when to prefer this over generate_animation, nor name quote_video_generation as the source of the quote, so the agent must infer the routing.

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

All AnimGen 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?