Skip to main content
Glama

Valmera — agentic AI video editor

by io.valmera
OverviewDiscussionsAdmin

Set frame

set_frame
Idempotent

PROJECT-SCOPED: this call acts only on the explicit project_id and returns the project identity with its result. Set the output aspect ratio for every render. ratio: source, 16:9, 9:16, 1:1 or 4:5; mode: crop (default), pad (black bars) or pad_blur (blurred backdrop). focus_x/focus_y aim the CROP at the subject (fractions of the source frame, (0,0) = top-left) — without them the crop is the dead-center window, which chops an off-center speaker. For 'make it 9:16' on real footage PREFER auto_reframe, which measures the subject and sets the focus for you. Finals compose on an HD canvas so new captions and branding stay sharp even on archival footage; this does not restore missing source detail. focus_track replaces the complete per-shot track: [{t0,t1,x,y,mode}] in SOURCE seconds. Read get_edl(frame) first; change only the desired spans. Tracks survive trims and speed changes; a span edge within 0.25s of a camera cut snaps onto the cut. picture=[left,top,right,bottom] optionally places the main picture and inserts inside a normalized output rectangle on black. Crop/fit and focus apply inside it, preserving native audio/transcript timing. For a 4:3 picture on 9:16: picture=[0,0.2890625,1,0.7109375]. A rounded card on a designed canvas needs none of this: set_picture_card reads the full source frame itself. Captions, headlines and branding stay at the full delivery resolution. set_frame writes STILL aims: it drops a face-following path auto_reframe measured (call auto_reframe again to re-measure one).

Input Schema

NameRequiredDescriptionDefault
modeNo
ratioYes
focus_xNo
focus_yNo
pictureNo
project_idYesRequired immutable scope for this call. Copy the id from list_projects/open_project/project_state; the active-project pointer is never used to guess.
focus_trackNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / picture
      Added value: +{
+  "items": {
+    "type": "number"
+  },
+  "maxItems": 4,
+  "minItems": 4,
+  "type": "array"
+}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare non-read-only, idempotent, non-destructive, but the description adds substantial context beyond them: project scoping and identity in the result, that tracks survive trims and speed changes, that a span edge within 0.25s snaps to a cut, and the destructive side-effect of dropping a measured face-following path.

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 core purpose and scoping, and nearly every sentence carries decision-relevant detail. It is dense and occasionally editorial ('which chops an off-center speaker'), running longer than strictly necessary, but little of it is filler.

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?

For a 7-parameter, low-coverage, no-output-schema mutation tool, the description covers scoping, return identity, defaults, geometry conventions, snapping behavior, and sibling alternatives. Nothing an agent needs to invoke it correctly appears to be missing.

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?

With schema coverage at only 14%, the description carries the load: it enumerates ratio and mode values with the crop default, defines focus_x/focus_y as fractions with (0,0)=top-left and the dead-center fallback, specifies focus_track as [{t0,t1,x,y,mode}] in SOURCE seconds, and gives a concrete picture=[0,0.2890625,1,0.7109375] example.

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 ('Set the output aspect ratio for every render') and immediately scopes it ('PROJECT-SCOPED: acts only on the explicit project_id'). It actively distinguishes itself from siblings by name, routing 9:16 work to auto_reframe and rounded cards to set_picture_card.

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?

Explicit when/when-not/alternatives: 'PREFER auto_reframe' for real footage, 'Read get_edl(frame) first; change only the desired spans,' and 'A rounded card on a designed canvas needs none of this: set_picture_card reads the full source frame itself.' It even warns that calling it drops an auto_reframe path and how to recover.

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