Skip to main content
Glama

dctl

Validate, write, read, list, and encrypt DCTL shaders for DaVinci Resolve, saving validated LUT files ready to apply with grade_lut.

Instructions

DCTL shaders. action: validate (source) | write (name + source → LUT/ClaudeMCP/.dctl, validated first; then use grade_lut with 'ClaudeMCP/.dctl') | read (name) | list | encrypt (path).

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": {
      "action": "<action>"
    },
    "name": "dctl"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
pathNo
actionYes
sourceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: write persists a file to a concrete path (LUT/ClaudeMCP/<name>.dctl) and validates before writing. However, it says nothing about overwrite behavior for an existing name, what encrypt does to the file (in place? output path?), whether any action requires elevated permissions, or what validate returns on failure.

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 but front-loaded and scannable via the pipe-delimited action list; nearly every token carries information. The arrow notation ('→ LUT/ClaudeMCP/<name>.dctl') and parenthetical parameter hints are compressed to the point of being slightly cryptic on first read, but no sentence is wasted.

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 four-parameter multiplexed tool with no annotations and no output schema, the definition covers inputs and write side effects well. It is incomplete on the return side: nothing indicates what validate or read yield (validation errors vs. shader text) or what list returns, which matters because the agent must act on those results.

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 0%, so this description is the only documentation, and it does real work: it maps each of the four parameters to the actions that use them and explains that name becomes a filename segment. The 'action' field has no enum in the schema, so the description effectively defines the allowed values. The gaps are minor — list requires no parameters and is not stated as such, and path is only tied to encrypt.

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 description names a specific resource (DCTL shaders) and enumerates five concrete actions, each with the parameter it consumes. It also names the sibling grade_lut as the downstream consumer of written LUTs, which helps separate this tool from the grading tools. It falls short of 5 only because the bare opener 'DCTL shaders.' does not itself state a verb until the action list is read.

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?

Per-action usage is spelled out: validate takes source, write needs name + source, read needs name, encrypt takes path. It goes further than most definitions by describing the workflow handoff — after write, call grade_lut with 'ClaudeMCP/<name>.dctl'. There is no explicit when-not guidance (e.g., when to read vs list, or what happens if a shader name already exists).

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