Skip to main content
Glama

grade_look

Build a creative color grade as a reusable 3D LUT and apply it to selected clips or a timeline node on display-referred Rec.709 footage.

Instructions

Build a creative grade as a 3D LUT and apply it to a node of clips (or 'timeline'). Works on display-referred (Rec.709) images. Parameters (neutral defaults): exposure (stops), contrast (1 = none; 1.2 = +20%) around pivot, saturation (1), vibrance (0..1), temperature (−1 cool … +1 warm), tint (−1 green … +1 magenta), lift/gamma/gain/offset (number or [r,g,b]; lift/offset default 0, gamma/gain 1), shadows/highlights (−1..1 tone lift/recover), fade (0..0.3 milky blacks), tint_shadows / tint_highlights ([r,g,b] colors like [0.0,0.05,0.1] for teal shadows) — e.g. teal & orange: tint_shadows=[0,0.04,0.08], tint_highlights=[0.08,0.04,0]. Returns the LUT path (reusable with grade_lut).

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": {
      "clips": "<clips>"
    },
    "name": "grade_look"
  }
}

Input Schema

NameRequiredDescriptionDefault
fadeNo
gainNo
liftNo
nameNo
nodeNo
sizeNo
tintNo
applyNo
clipsYes
gammaNo
pivotNo
offsetNo
shadowsNo
contrastNo
exposureNo
vibranceNo
highlightsNo
saturationNo
temperatureNo
tint_shadowsNo
tint_highlightsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It discloses that the tool builds and applies a grade to a node, works on Rec.709 images, lists parameter defaults, and returns a LUT path, but it does not state whether an existing node grade is overwritten, whether permissions are required, or whether the operation is reversible.

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?

The description front-loads the purpose and return value, then packs parameter semantics densely with little wasted text. It is appropriately sized for a 21-parameter tool, though a more scannable layout would improve readability.

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 21-parameter, unannotated mutation tool with no output schema, the description is substantial but not complete. It clarifies the color math and the LUT return value, but omits critical structural parameter semantics and safety or idempotency context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 21 parameters and 0% schema description coverage, the description must compensate, and it does explain most color parameters with ranges, defaults, and a teal-and-orange example. It still leaves important structural parameters undocumented, including the required clips parameter, node, apply, name, size, and pivot semantics, so an agent cannot fully infer the invocation format.

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: build a creative grade as a 3D LUT and apply it to a node of clips or timeline. It also names the image domain (display-referred Rec.709) and ties the returned LUT to grade_lut, giving an agent a clear way to distinguish it from sibling grading tools.

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

Usage Guidelines3/5

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

Gives an important applicability constraint, namely that it works on display-referred Rec.709 images, and mentions reuse via grade_lut. However, it does not explicitly say when to choose this over grade_lut, grade_cdl, or other grade tools, so usage is implied rather than routed.

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