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

Add Layer

add_layer

Creates and configures After Effects layers such as solids, text, shapes, footage, cameras, lights, and meshes with position, timing, fit, and styling options.

Instructions

Add a layer. item_id: footage/precomp source. center: camera/light. position with 3 values turns 3D on. box_size: box text; text_style as set_text. anchor moves the anchor onto the content (as set_anchor) before position, so position places e.g. the text's center. shape: a shape layer's first shape (as add_shape). mesh: a 3D primitive, centred on position, color is its base color (After Effects 26.3+; moves the comp to the renderer that draws meshes, reported as renderer_changed; list_properties has its size, bevel and slices). fit_to (shape): a rect that keeps fitting that layer's content + padding (a highlight behind text). fit: scale to cover or fit inside the comp frame. Timing: in/out are comp times; source_in is the source time shown at in (no start maths); stretch in percent (200 = half speed).

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>",
      "kind": "<kind>"
    },
    "name": "add_layer"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
comp_idYes
optionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.25.0
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "solid",
      -  "text",
      -  "shape",
      -  "null",
      -  "adjustment",
      -  "footage",
      -  "precomp",
      -  "camera",
      -  "light"
      -]New value: +[
      +  "solid",
      +  "text",
      +  "shape",
      +  "null",
      +  "adjustment",
      +  "footage",
      +  "precomp",
      +  "camera",
      +  "light",
      +  "mesh"
      +]
    • addedInput schema / properties / options / properties / mesh
      Added value: +{
      +  "properties": {
      +    "emission": {
      +      "items": {
      +        "type": "number"
      +      },
      +      "type": "array"
      +    },
      +    "emission_intensity": {
      +      "type": "number"
      +    },
      +    "metallic": {
      +      "type": "number"
      +    },
      +    "roughness": {
      +      "type": "number"
      +    },
      +    "type": {
      +      "enum": [
      +        "cube",
      +        "sphere",
      +        "plane",
      +        "cylinder",
      +        "cone",
      +        "torus"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed1 schema field changedv2.23.0
    • removedInput schema / properties / options / properties / text_style / additionalProperties
      Removed value: -{}
  3. First observedv2.22.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent behavior. The description adds real side-effect disclosure beyond that: 3-value position turns 3D on, mesh moves the comp to a mesh-capable renderer and reports renderer_changed, anchor is set before position. But it never states what is returned (created layer id?) or how failures surface, which matters for a creation tool with no output schema.

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?

Extremely dense with no filler: each clause conveys a distinct behavioral fact and the core action is front-loaded. The telegraphic, semicolon-chained style ('center: camera/light') is compact but harder to scan than a bulleted option list, so structure is good rather than excellent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a high-complexity create tool with deeply nested options and no output schema, the description covers the subtle semantics well but omits the return value and leaves a large share of the option surface undocumented. An agent can construct common calls correctly but must inspect the schema for many fields.

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 0% schema description coverage, the description carries the burden and does so for the confusing options: item_id source, center for camera/light, box_size vs text_style, anchor semantics and ordering relative to position, fit_to as a live-fitted backdrop, fit cover/contain, and in/out/source_in/stretch timing. Many options remain unmentioned (name, size, color, duration, start, light_type, three_d, most shape sub-fields), so it is strong but not complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening verb+resource ('Add a layer') plus the parameter walkthrough makes clear this creates a new layer of a given kind inside comp_id. Cross-references ('as add_shape', 'as set_text', 'as set_anchor') help an agent separate creating a layer from configuring an existing one, though it never explicitly contrasts with duplicate_layer or set_layer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use/when-not guidance: nothing says to prefer duplicate_layer or add_shape, or what prerequisites exist (comp must be open, AE version for mesh). The cross-references to set_text/set_anchor/add_shape describe equivalence of options, not tool selection, so guidance remains implicit at best.

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