Skip to main content
Glama
AE Motion MCP
by dha-aa

Review Motion

review_motion
Read-onlyIdempotent

Critique a comp's animation without rendering to catch easing, holds, timing, overlap, visibility, text-size, and safe-margin issues, then fix every warning.

Instructions

Critique a comp's animation without rendering (cheap, no image): linear easing, holds over max_hold (changes too small to see don't count as motion: fix holds with animate push / drift), a first move later than 0.3 s, layers moving in unison, entrances with no animation, moves cut off by out points, jumps, text under min_text px (default 3% of the comp's short side), share of moves on beat markers; layers hidden behind opaque ones (3D: by depth), off screen, a background that stops filling the frame, text partly covered, text crossing the 5% title-safe margin (vertical comps: the top 10% and bottom 20% social apps cover) (scene false skips). Run after each scene and fix every warning.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "comp_id": "<comp_id>"
    },
    "name": "review_motion"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNoList info notes too (default: counted in stats.info)
maxNoIssues listed (default 30; more_issues counts the rest)
sceneNo
comp_idYes
max_holdNo
min_textNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.26.0
    • addedInput schema / properties / max / description
      Added value: +"Issues listed (default 30; more_issues counts the rest)"
  2. First observedv2.22.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare the operation is read-only, idempotent, and non-destructive. Beyond that, the description discloses that no rendering occurs, lists the warning categories, gives threshold behavior such as max_hold and min_text defaults, and explains that scene=false skips scene checks. It does not describe the exact warning output structure, but it adds substantial behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is information-dense and every check appears relevant, but it is delivered as one long run-on sentence with nested parentheticals. Front-loading the purpose is good, yet the lack of structure makes the extensive rule set harder to scan than necessary.

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 complex review tool with six parameters and no output schema, the description covers the important validation categories, defaults, and usage timing. It leaves the exact return format implicit, but an agent has enough information to invoke the tool correctly and understand the kinds of warnings it produces.

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 only 33%, so the description must carry weight. It clarifies max_hold, min_text with its 3% default, and scene=false behavior, while comp_id is obvious and all/max are already described in the schema. This compensates for most of the undocumented parameters, though it does not explicitly explain max or all in the description itself.

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 states a specific verb and resource: critique a comp's animation. It also distinguishes itself from rendering-based siblings by saying it runs 'without rendering (cheap, no image)' and then enumerates the exact motion and layout issues it checks.

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?

It gives a clear usage context ('Run after each scene') and a follow-up action ('fix every warning'). It also clarifies one conditional mode ('scene false skips'), though it does not explicitly name when to prefer this over rendering or preview alternatives.

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