Skip to main content
Glama

Valmera — agentic AI video editor

by io.valmera
OverviewDiscussionsAdmin

Watch the video itself

watch_video
Read-only

WATCH THE VIDEO YOURSELF — the real file, pixels and audio, not a description of it. Use this instead of look_at whenever your own model can take video input: look_at sends frames to Valmera's vision model and hands you back a PARAGRAPH, while this hands you the footage. kind 'timeline' (default) is the assembled program as the viewer sees it — it renders the current edit first if it has not been rendered; 'source' is the raw uploaded footage; 'asset' is one uploaded clip (pass asset_key). start/end watch a window rather than the whole thing. The reply, in this call: a direct download link to a plain MP4 (structuredContent.url too), plus — unless frames=false — ONE sheet of sampled frames as an image and the window's sound as audio when it fits. Cheap: normally it hands over a file that already exists, untouched.

Input Schema

NameRequiredDescriptionDefault
endNoWatch up to this second.
kindNoDefault 'timeline' — the current edit.
startNoWatch from this second. OUTPUT seconds for 'timeline', source seconds otherwise.
framesNoDefault true. False returns only the video file/link and suppresses sampled frame sheets plus their attached audio; use false for clean external ASR retrieval.
max_mbNoShrink to about this many megabytes. Use when your model has a file-size limit.
renderNokind='timeline': false watches the last render that exists instead of rendering the current edit, and says how stale it is. Default true.
deliveryNoA download link either way. Embedding the file in the reply is off on this deployment.
asset_keyNokind='asset' only: the storage_key list_assets prints.
max_heightNoCap the picture height (e.g. 360). Never up-scales.
project_idYesRequired immutable project scope.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnly, non-destructive), but the description adds real behavioral context: it renders the current edit on demand for kind='timeline', embedding is disabled on this deployment so delivery is always a link, and it is cheap because it usually hands over an existing file untouched. It does not describe limits on window length or sampling density.

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 decisive differentiator (real footage vs. a paragraph), then the kind modes and the reply shape. Dense but each clause adds something; the all-caps opening and em-dash asides are slightly noisy.

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?

With no output schema, the description carries the return-value burden and does: a plain MP4 download link, structuredContent.url, one sampled frame sheet plus window audio unless frames=false. Nothing an agent needs to invoke it correctly is missing.

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?

Schema coverage is 100% so the baseline is 3, but the description goes further by tying parameters to intent — frames=false for clean external ASR retrieval, max_mb for model file-size limits, and start/end as a window versus the whole program.

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+resource ('WATCH THE VIDEO YOURSELF — the real file, pixels and audio') and explicitly contrasts itself with the sibling look_at, so an agent can distinguish it without opening either 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 selection rule ('Use this instead of look_at whenever your own model can take video input'), explains what the alternative returns (a paragraph), and enumerates when each kind and modifier (start/end, max_mb, frames=false) applies.

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

All Valmera — agentic AI video editor toolsInspect
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