BlitzReels Video Editor

Generate Video

generation_video_create

Idempotent

Queue an AI video generation into the BlitzReels media library, from a prompt or from an existing image asset. Spends AI credits and returns a job to poll with generation_jobs_get.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`seed`	No	Optional seed for reproducible output.
`model`	No	Video model. Supported durations and text-to-video vs image-to-video differ per model; call generation_options_list first.	wan-2.1
`prompt`	Yes	What should happen in the shot (3-5000 characters).
`folderId`	No	Optional media library folder ID.
`resolution`	No	Seedance 2.5 output resolution.
`aspectRatio`	No	Output aspect ratio.	9:16
`workspaceId`	No	Optional workspace ID. Defaults to the user's default workspace. UUID string.
`generateAudio`	No	Generate audio alongside the video when supported.
`sourceAssetId`	No	Source image asset ID. Required by image-to-video models.
`idempotencyKey`	No	Retry key. Reuse only with identical inputs.
`negativePrompt`	No	What to avoid in the shot.
`durationSeconds`	No	Clip length in seconds (2-30). Must be supported by the chosen model.
`referenceAssetIds`	No	Reference image asset IDs. Seedance 2.5 accepts 29 plus sourceAssetId, for 30 images total; other models accept up to 4.
`referenceAudioAssetIds`	No	Seedance 2.5 reference audio asset IDs. Unsupported by other models.
`referenceVideoAssetIds`	No	Seedance 2.5 reference video asset IDs. Unsupported by other models.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`generation`	Yes

TDQS

A4.2/5.0

Behavior4/5

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

The description discloses important behavior beyond the annotations: the operation is asynchronous ('Queue', 'returns a job to poll') and has a cost ('Spends AI credits'). Annotations already signal idempotency and non-destructiveness, and the description adds context without contradicting them.

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 deliver the primary action, the domain, the input modes, the cost, and the follow-up polling mechanism with no filler. The most decision-relevant information is front-loaded.

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 15-parameter tool, the description is economical but sufficient because the schema covers parameter details and an output schema is present. It provides the key operational knowledge an agent needs: async job semantics, cost, and where results land.

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 description coverage is 100%, so the schema already fully documents all 15 parameters. The description adds only a brief mapping to the two main input modes (prompt vs. existing image asset), which aligns with prompt and sourceAssetId, but does not substantially extend parameter understanding.

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 uses a specific verb ('Queue'), names the resource ('AI video generation into the BlitzReels media library'), and clarifies the input modes ('from a prompt or from an existing image asset'). This clearly distinguishes it from sibling generation tools like generation_image_create or generation_music_create.

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?

The description states the key context: it queues an asynchronous video generation, spends AI credits, and returns a job to poll with generation_jobs_get. It does not explicitly contrast with every sibling generation tool, but the video-specific scope and prompt/image input are enough to guide selection.

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

All BlitzReels Video Editor tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0

Disambiguation3/5

Most tools use clear domain prefixes, but several boundaries are fuzzy: clips_get and clips_manage both expose clip/export status, and update_timeline_clip overlaps with timeline_edit_apply for trim/duration changes. Detailed descriptions mitigate this, but an agent could still select the wrong tool for clip inspection or timeline edits.

Naming Consistency3/5

All names are snake_case and mostly readable, but the server mixes verb-first names (add_text_overlay, delete_timeline_items, update_timeline_clip) with noun-first domain-action names (clips_create, generation_*_create, media_import_*). The domain-prefix pattern dominates, yet the inconsistent verb placement makes the convention only partially predictable.

Tool Count1/5

58 tools is far beyond the 25+ threshold and matches the rubric's 50+ extreme-mismatch example. Even though the domain is broad, this surface would be easier for an agent to navigate if split into focused servers for media, generation, timeline editing, clips, and workflows.

Completeness3/5

Core video-editing flows are well represented: project creation/inspection, timeline item editing/deletion, media import/upload, AI generation, exports, and clips. However, lifecycle gaps remain—no project update/delete, no media asset deletion, no delete for characters or story kits, and no export cancellation—so some user requests will dead-end.

Resources

Need Help?