Valmera — agentic AI video editor

Set motion graphic

set_motion_graphic

Idempotent

PROJECT-SCOPED: this call acts only on the explicit project_id and returns the project identity with its result. Patch an existing motion graphic by id — window, params (merged into the current ones), template, layer, html or caption muting (mute_captions as in add_motion_graphic; the drawn box captions keep clear of is re-measured). Its owned sound cues move with it; sfx=true re-derives them, sfx=false removes them. A behind_subject graphic whose window changes is re-measured against its new footage. Every patch re-runs the face and safe-area keep-out (see add_motion_graphic): a y that would cover the face is moved and reported; allow_face_overlap=true keeps it (false clears that). A number graphic is re-landed on its spoken number like add_motion_graphic; the window, cut-snap, size, series, tier and Look checks re-run too (a word made tier='hero' goes behind the speaker unless layer is passed). Modify instead of removing and re-adding.

Input Schema

Name	Required	Description
`id`	Yes
`box`	No
`end`	No
`sfx`	No
`html`	No
`layer`	No
`start`	No
`params`	No	Template parameters (see list_motion_templates).
`purpose`	No
`template`	No
`project_id`	Yes	Required immutable scope for this call. Copy the id from list_projects/open_project/project_state; the active-project pointer is never used to guess.
`mute_captions`	No	Omit (default): captions drop the words it shows; every other heard word stays captioned beside it. true = the same (no graphic mutes a whole window: every heard word reaches the screen once), muting only where no band is clear of it; false = captions keep running (a shown number/starred word is still not repeated).
`allow_face_overlap`	No	Keep a deliberate placement over the face (skips the keep-out move).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 10, 2026

changedInput schema / properties / mute_captions / description

Previous value: -"Omit (default): one reading path, captions drop the words it shows and yield to its phrase until it leaves. true = no captions in its window; false = captions keep running (a shown number/*starred* word is still not repeated)."New value: +"Omit (default): captions drop the words it shows; every other heard word stays captioned beside it. true = the same (no graphic mutes a whole window: every heard word reaches the screen once), muting only where no band is clear of it; false = captions keep running (a shown number/*starred* word is still not repeated)."

Changed1 schema field changedOct 10, 2026

changedInput schema / properties / mute_captions / description

Previous value: -"Omit (default) for word-level: captions drop only the spoken words this graphic shows. true = no captions for its whole window; false = captions keep running (a number/*starred* word it shows is still not repeated)."New value: +"Omit (default): one reading path, captions drop the words it shows and yield to its phrase until it leaves. true = no captions in its window; false = captions keep running (a shown number/*starred* word is still not repeated)."

Changed2 schema fields changedOct 10, 2026

addedInput schema / properties / allow_face_overlap

Added value: +{
+  "description": "Keep a deliberate placement over the face (skips the keep-out move).",
+  "type": "boolean"
+}

addedInput schema / properties / mute_captions / description

Added value: +"Omit (default) for word-level: captions drop only the spoken words this graphic shows. true = no captions for its whole window; false = captions keep running (a number/*starred* word it shows is still not repeated)."

AddedOct 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare mutation, idempotency and non-destructiveness, and the description adds rich behavior on top: sfx re-derives vs removes owned sound cues, window changes trigger re-measurement, the face/safe-area keep-out re-runs and reports a moved y, and allow_face_overlap toggles it. Project-scoping and the no-guessing rule for project_id are also disclosed.

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 PROJECT-SCOPED constraint and dense with per-branch behavior; every sentence carries information. It is a single run-on paragraph with many inline parentheticals rather than cleanly structured sections, so parsing effort is higher than ideal, but length is largely justified by the tool's complexity.

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 13-param mutation with no output schema and low schema coverage, the description covers the important behavioral branches (sfx, re-measurement, keep-out, number re-landing) and defers return details implicitly via 'returns the project identity.' A few parameters remain unaddressed, so it is strong but not exhaustive.

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?

With schema coverage at only 31% across 13 params, the description compensates well: it explains that params are merged into current ones, that sfx=true re-derives and sfx=false removes cues, and that allow_face_overlap=true keeps a face placement. It does not fully define 'purpose', 'box', or start/end semantics, leaving some gap.

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 and resource: "Patch an existing motion graphic by id." It also distinguishes itself from siblings by explicitly saying "Modify instead of removing and re-adding," differentiating it from remove_motion_graphic/add_motion_graphic. An agent can identify the operation without opening the schema.

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?

Provides clear usage direction ("Modify instead of removing and re-adding") and repeatedly routes to add_motion_graphic as the semantic reference for related behaviors. However it never states explicit when-not conditions or a full alternation against add_motion_graphic/remove_motion_graphic beyond the closing directive.

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 tools Inspect

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.

Set motion graphic

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources