Skip to main content
Glama

timeline_ai

Automate DaVinci Resolve timeline edits by detecting scene cuts, generating subtitles, normalizing audio, auto-aligning clips, converting to stereo, analyzing Dolby Vision, and managing multicam.

Instructions

Timeline-level tools. detect_scene_cuts; create_subtitles (options: language AUTO_CAPTION_*, captionPreset, charsPerLine, lineBreak, gap); normalize_audio (items; options: normalizationMode, targetLevel, targetLoudness, setLevelMode — see list_api_methods('Timeline') for modes); auto_align (items; options SyncUsing, UseTrack); convert_to_stereo; dolby_vision_analysis (items); smart_switch (one multicam item; SmartSwitchSettings); flatten_multicam (one item; options {grade: FLATTEN_MULTICAM_*}). Constant names in options are converted.

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": "timeline_ai"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsNo
actionYes
optionsNo
timelineNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is partly covered. Beyond that, the description adds real invocation-shape detail (which actions accept items, cardinality limits, per-action option keys) and one genuine behavioral note, 'Constant names in options are converted', but says nothing about whether these operations are long-running/asynchronous, whether analysis results persist to the timeline, or what a call returns.

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?

It is front-loaded with the scope label, then a semicolon-delimited list of actions with just enough parenthetical option detail. Every fragment carries information an agent needs for dispatch; nothing is repeated from the schema except the action names in condensed form.

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 an eight-action dispatcher with no schema descriptions and no output schema, the definition covers actions, per-action option keys, item cardinality, and constant conversion well. The gaps are the unmentioned 'timeline' parameter and the absence of any return-value or side-effect description, which matters more here because no output schema exists to carry that information.

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 does substantial compensating work: it maps option keys to specific actions (language/captionPreset/charsPerLine/lineBreak/gap for create_subtitles; normalizationMode/targetLevel/targetLoudness/setLevelMode for normalize_audio; SyncUsing/UseTrack for auto_align; SmartSwitchSettings for smart_switch; {grade: FLATTEN_MULTICAM_*} for flatten_multicam) and explains the constant-name conversion behavior. The fourth parameter, 'timeline', is never mentioned, and 'items' is not explained in terms of clip vs. track identifiers.

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 opens with 'Timeline-level tools' and then enumerates the eight concrete operations (detect_scene_cuts, create_subtitles, normalize_audio, auto_align, convert_to_stereo, dolby_vision_analysis, smart_switch, flatten_multicam), so an agent can tell this is a timeline-scoped AI dispatcher rather than an item-level or project-level tool. The action names are specific verbs, but there is no explicit statement separating this from related AI tooling beyond the 'timeline-level' scope label.

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?

Usage is only implied by the 'Timeline-level tools' label and by embedded target constraints ('one multicam item', 'one item', 'items'), which hint that some actions operate on selected items. There is no explicit when-to-use/when-not, no statement of prerequisites, and no guidance on choosing between the individual actions or the underlying API path (the only pointer, list_api_methods('Timeline'), is for reading mode names, not for tool selection).

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