Skip to main content
Glama

manage_preset

Load, save, update, delete, import, or export DaVinci Resolve presets for layout, render, burn-in, keyboard, preferences, and project settings.

Instructions

Load / save (as new, from current state) / update / delete / import (from path) / export (to path) a preset. Not every kind supports every action (e.g. render presets cannot be 'loaded' here: use set_render_settings with preset=...).

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": {
      "kind": "<kind>",
      "action": "<action>"
    },
    "name": "manage_preset"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
nameNo
pathNo
actionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior3/5

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

Annotations declare a non-read-only, non-destructive, closed-world tool, and the description adds meaningful behavior beyond them: save creates a new preset from current state, import/export are path-backed, and action support varies by kind. However, it says nothing about the permanence of delete, whether import overwrites an existing preset, or whether save/update fail on a name collision — consequences an agent needs before mutating state. The listed delete action also sits in tension with destructiveHint=false, so the description should have clarified the scope of what gets destroyed.

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

Conciseness5/5

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

Two sentences, front-loaded with the verb enumeration, with no filler. The action list is compressed into a single slash-separated line and the exception is placed immediately after the capability statement, where an agent will actually read it.

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 four-parameter dispatch tool with no output schema, the definition covers the resource, the action set, the path parameters, and the main cross-tool routing case — enough to call it correctly most of the time. What is missing is the kind x action support matrix (sketched only by example) and any statement about return values or failure modes when an unsupported combination is requested.

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 description coverage is 0%, so the description must carry the load, and it does cover a lot: it enumerates the action enum in prose and binds `path` to import/export, and explains that `kind` gates which actions are legal. It does not explain `name` — whether it is required for load/update/delete, what the null default means, or how 'save as new' uses it — which is the remaining semantic hole across the four parameters.

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 concrete resource (preset) plus the full verb set it dispatches (load/save/update/delete/import/export), with a parenthetical clarifying what 'save' means (as new, from current state). It also names the sibling that covers the one action it does not handle, so an agent can separate it from set_render_settings and apply_fairlight_preset at a glance.

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 an explicit when-not plus the correct alternative: render presets cannot be 'loaded' here and must go through set_render_settings with preset=... That is real routing guidance rather than implied usage. The gap is that the per-kind restriction is presented only as an 'e.g.', so the agent is told some kind/action pairs are invalid but not which ones, leaving trial-and-error for layout, burn_in, keyboard, user_preferences and project_settings.

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

Deploy Server

Other Tools