Skip to main content
Glama

video_generate

Generate short video clips from text prompts, optionally guided by start/end frames or reference media, with batching for multiple clips and job status tracking.

Instructions

For a user's video request, load the generating-videos skill BEFORE calling this — it picks the right model and builds the motion prompt (this tool does neither, and calling it raw gives weak, generic clips). Generate one or many short video clips from text prompts, optionally guided by a start (and end) frame or by reference images, videos, or audio. Pass requests: ONE object per clip (wrap even a single clip — { requests: [ { prompt } ] }); add more objects (up to 10) to batch DIFFERENT clips in one call, and repeat an object for variations of one prompt — a single approval covers the batch. Models differ in the aspect ratios, durations, resolutions, and media they accept — call list_video_models to check. Video generation is long-running: each clip is submitted and polled for you. A clip that finishes in time returns a hosted video URL plus a local file path; a clip still generating returns {status:"pending", ...} (a job handle, NOT an error) — pass that exact handle to job_status to retrieve it, and never re-submit a pending clip. Set dry_run=true to preview the exact requests without generating (no credits spent).Each entry in results is one of three things: finished media; a {status:"pending", ...} job handle to rejoin with job_status; or a failure carrying ok: false and an error. A failed entry is terminal — report its error and never poll or re-submit it. Read every entry rather than the top-level counters alone.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runNoIf true, return the requests that would be sent (keys masked), make no API call.
requestsYesOne object per clip (wrap even a single clip); add more objects to batch different clips in one call (up to 10).
Behavior5/5

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

With no annotations provided, the description carries full behavioral burden. It discloses long-running async behavior with polling, that a pending result is a job handle not an error, that failures are terminal with ok:false and error, that dry_run spends no credits, that durations snap to valid values, and that start/end frames require each other and cannot be combined with reference_* inputs. This is comprehensive behavioral disclosure.

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 long but dense with essential information—prerequisite skill, batching, model differences, async behavior, result types, and failure handling. Every sentence earns its place, though the run-on structure makes it less scannable than it could be. It is appropriately front-loaded with the most critical warning about the skill prerequisite.

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?

The tool is complex (batching, multiple reference types, long-running jobs, model variations) and has no output schema, yet the description covers all key aspects: purpose, prerequisites, model checking, job handles, failure terminality, dry_run, result entry types, and edge cases like snappng and incompatible inputs. This leaves no significant gap for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema description coverage is 100%, the description adds crucial semantics not in the schema: wrapping single clips in an array, batching up to 10 different clips, repeating an object for variations, a single approval covering the batch, and dry_run previewing requests without generation. It clarifies how requests should be structured and adds the pending-result meaning, which the schema cannot convey.

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 'Generate one or many short video clips from text prompts' with optional frame/reference guidance, giving a specific verb and resource. It also distinguishes itself from siblings by warning that it does not pick the model or build the motion prompt (that's the generating-videos skill), and by pointing to list_video_models for model selection, seting it apart from video_stitch, job_status, and image_generate.

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?

Explicitly instructs to 'load the generating-videos skill BEFORE calling this' because the tool itself 'does neither' model selection nor prompt building, and calling raw gives weak clips. It also directs users to call list_video_models to check model-specific capabilities, and to use job_status for pending jobs, with a warning never to re-submit pending clips or poll failed entries. This gives clear when-to-use and when-not-to-use guidance with named alternatives.

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/SupercmoHQ/superCMO-skills'

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