MeiGen AI Design MCP

Overview Schema Source Related Servers Discussions Admin

render_video_draft

DestructiveIdempotent

Render an owned completed video draft as a paid 1080p final after confirming credits and authorization; reuse inputs on interruption and render before draft expiration.

Instructions

Render an owned completed draft as a separate paid 1080p final. Show the draft, quote check_generation seedanceDraft.finalCredits and obtain authorization first. This is the full final cost, not a price difference. Drafts expire at expiresAt. Reuse the same requestId/inputs on interruption. Only an explicitly authorized replacement after failure supplies retryFailedGenerationId and a new requestId. No changed prompt/references.

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": {
      "requestId": "<requestId>",
      "sourceDraftGenerationId": "<sourceDraftGenerationId>",
      "confirmedCredits": "<confirmedCredits>"
    },
    "name": "render_video_draft"
  }
}

Input Schema

Name	Required	Description	Default
`requestId`	Yes
`confirmedCredits`	Yes
`retryFailedGenerationId`	No
`sourceDraftGenerationId`	Yes

Output Schema

Name	Required	Description	Default
`urls`	Yes
`error`	No
`status`	Yes
`deduped`	No
`modelId`	No
`success`	Yes
`imageUrl`	No
`provider`	No
`videoUrl`	No
`mediaType`	No
`requestId`	No
`savedPath`	No
`nextAction`	No
`creditsUsed`	No
`generationId`	No
`vectorOutput`	No
`creditsStatus`	No
`failureDetail`	No
`seedanceDraft`	No
`receiptWarning`	No
`downloadWarning`	No
`observationEnded`	No
`pollAfterSeconds`	No
`requestedMediaType`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv3.4.0Nov 6, 2026

changedOutput schema / properties / failureDetail / enum

Previous value: -[
-  "video_edit_duration",
-  "reference_video_frame_rate"
-]New value: +[
+  "video_edit_duration",
+  "reference_video_frame_rate",
+  "midjourney_profile_not_found",
+  "midjourney_sref_invalid"
+]

addedOutput schema / properties / vectorOutput

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "height": {
+      "maximum": 4096,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "url": {
+      "format": "uri",
+      "pattern": "^https:\\/\\/images\\.meigen\\.(?:ai|art)\\/[A-Za-z0-9_./-]+\\.svg$",
+      "type": "string"
+    },
+    "width": {
+      "maximum": 4096,
+      "minimum": 1,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "url",
+    "width",
+    "height"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv3.3.0Oct 21, 2026

addedOutput schema / properties / failureDetail

Added value: +{
+  "enum": [
+    "video_edit_duration",
+    "reference_video_frame_rate"
+  ],
+  "type": "string"
+}

Addedv3.2.0Oct 15, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true, idempotentHint=true and openWorldHint=true, but the description adds the economically critical facts the annotations cannot convey: this is a real charge, it is the full final cost rather than a price difference, and drafts expire at expiresAt. It also specifies interruption recovery (reuse the same requestId/inputs) and the authorization gate for retries, which is exactly the behavioral burden a spending tool needs.

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 action and cost model, then the prerequisites, then edge cases, so the most important facts arrive first. It is dense and telegraphic, with fragments like 'No changed prompt/references.', which cost some readability but each sentence still carries distinct operational information.

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?

For a destructive, credit-spending tool with an output schema (so return values need no prose), the description covers cost, expiry, idempotent retry and authorization, which is nearly the full picture. The residual gap is the contradiction between the 'inputs' wording and a schema that forbids additional properties, plus no statement of what happens to credits on a failed render.

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?

With 0% schema description coverage, the description carries the full load and largely delivers: requestId is explained via the interruption/retry rules, sourceDraftGenerationId via 'owned completed draft', confirmedCredits via the check_generation quote, and retryFailedGenerationId via the authorized-replacement condition. It stops short of explicitly binding the quoted value to confirmedCredits, and it refers to 'inputs' even though additionalProperties is false and no such parameter exists, leaving a small ambiguity.

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 ('Render an owned completed draft as a separate paid 1080p final') and immediately distinguishes the output from its input – a separate, paid, higher-resolution artifact rather than an edit of the draft. An agent can tell this apart from generate_video or check_generation 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 an explicit ordered procedure: show the draft, quote check_generation's seedanceDraft.finalCredits, obtain authorization, then call. It also names the only sanctioned exception path (an explicitly authorized replacement after failure) and the condition that selects it, plus a clear exclusion ('No changed prompt/references').

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

Deploy Server