Skip to main content
Glama

generate_video

Create videos from text prompts or combine an image with a prompt to generate video. Supports customizable duration, aspect ratio, and output directory.

Instructions

Generate a video from a text prompt (text-to-video) or from an image + prompt (image-to-video, ark/veo). Available providers: none configured. Default: none.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoModel ID to use (optional, uses provider default if omitted). Check 'providers://models' resource for available models.
promptYesText prompt describing the video to generate
durationNoVideo duration in seconds (5 or 10). Default: 5
providerNoProvider to use: . Default: None
image_urlNoReference image for image-to-video generation (ark/veo). Accepts: local file path, HTTP URL, or gs:// URI. Optional.
aspect_ratioNoAspect ratio: 16:9, 9:16, or 1:1. Default: 16:916:9
output_directoryNoDirectory to save video. Optional.
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It adds meaningful transparency by disclosing that no providers are configured, which is a significant behavioral limitation. However, it does not explain the asynchronous nature of video generation (evidenced by sibling query_video_status) or what happens after a successful generation (output location, status polling, or result format). This gap is notable for a generation tool with no annotations or output schema.

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?

The description is front-loaded with the core purpose in the first sentence, and the second sentence efficiently conveys the provider limitation. It is appropriately brief, though 'Default: none' repeats information already in the schema (provider default). The 'none configured' statement is necessary for behavioral transparency, so the redundancy is minor. Overall it earns its place, but a slightly clearer tie-in to the provider default would be ideal.

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

Completeness2/5

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

Despite having 7 schema-documented parameters, the description lacks essential lifecycle context. It does not mention that generation is likely asynchronous, that users should poll via query_video_status, or where the output video is saved. The disclosure that no providers are configured is a strong caveat, but it leaves the user wondering whether the tool returns an error immediately or attempts a fallback. Without annotations or an output schema, this is a significant completeness gap.

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%, with all 7 parameters described in detail (e.g., image_url for ark/veo, duration options 5 or 10). The description adds high-level context (text vs image modes) that maps to prompt and image_url, but it does not provide per-parameter semantics beyond what the schema already states. Given full schema coverage, the description's contribution is minimal but non-zero, so baseline 3 is appropriate.

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 clearly states the tool's function with specific verbs: 'Generate a video from a text prompt (text-to-video) or from an image + prompt (image-to-video, ark/veo).' It distinguishes two modes and names the resource (video). This is unambiguous and effectively differentiates from sibling tools like query_video_status and list_providers, which serve obviously different purposes.

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 provides clear context on when to use the tool (for video generation) and distinguishes between text-to-video and image-to-video workflows. It also discloses the critical constraint 'Available providers: none configured. Default: none,' which implicitly advises that the tool is not actionable until providers are set up. No explicit exclusion against alternatives is needed since no sibling tool generates videos.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ZenforceTaiji/MCP-AI'

If you have feedback or need assistance with the MCP directory API, please join our Discord server