Skip to main content
Glama

Plan Reaction Captions

plan_reaction_captions
Read-onlyIdempotent

Generate a local, speaker-colored reaction caption plan from a word timeline and speaker palette, merging short words, stacking overlaps, and leaving unknown speakers uncolored.

Instructions

Plan stacked, speaker-colored reaction captions from a word timeline and an explicit speaker palette. Flash-length words merge, overlaps stack, and unknown speakers stay uncolored. Local-only; never changes Premiere.

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": {
      "word_timeline": "<word_timeline>",
      "speaker_palette": "<speaker_palette>"
    },
    "name": "plan_reaction_captions"
  }
}

Input Schema

NameRequiredDescriptionDefault
frame_rateNoSequence frame rate used to snap times to frames; defaults to 30.
shot_changesNoOptional labeled cut points. A matching speaker's caption will not start before they appear on screen when a readable hold remains.
max_cue_charsNoLongest caption text before a cue is split at a word boundary; defaults to 84 (two 42-character lines).
word_timelineYesCaller-supplied word-timed transcript for one Premiere source item. Words must be ordered by start time and bound to the transcript revision returned by get_clip_transcript_uxp. Different labeled speakers may overlap; same-speaker words may not, even when another speaker is between them.
max_cue_secondsNoLongest time one caption stays up before it is split; defaults to 6.
speaker_paletteYesKnown speakers and their exact #RRGGBB colors. Missing labels are returned as uncertain and never receive a guessed color.
min_hold_secondsNoMinimum duration kept after clamping a cue to a shot change; defaults to 0.35.
merge_gap_secondsNoSame-speaker words closer than this become one cue; defaults to 0.12 so a short pause can start a new line.
combine_gap_secondsNoMaximum gap when combining a flash cue with the next same-speaker cue; defaults to 0.8.
expected_cep_targetNoOptional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
min_solo_cue_secondsNoCues shorter than this merge with the next same-speaker cue; defaults to 0.45.
expected_project_pathNoOptional absolute saved-project path. Every generated CEP command refuses before its body when the active project differs or is unsaved. UXP commands refuse this CEP-only guard; local-only tools do not inspect Premiere. Omit to keep existing behavior.

Output Schema

NameRequiredDescriptionDefault
okYesWhether the tool completed successfully.
dataNoTool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it.
toolYesThe registered MCP tool name.
errorNoFailure detail when ok is false.
receiptNoVersioned common mutation receipt; success never implies rendered verification.
idempotencyNoPresent when idempotency_key deduplicated this call: replayed is true when the original outcome was returned instead of running again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.30.0

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the read-only/idempotent annotations, it discloses key behavior: flash-length words merge, overlaps stack, unknown speakers stay uncolored, and nothing is written to Premiere. It could still say more about the returned plan or edge-case handling, but the essential behavioral traits are present.

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?

Three sentences, front-loaded with purpose and behavior, with no wasted wording. The safety note is placed last where it is easy to scan.

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

Completeness5/5

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

The tool has a rich input schema, an output schema, and detailed annotations, so the description need not restate parameter details or return values. It supplies the key missing conceptual context: what is planned, what merge/stack behavior to expect, and that it is local-only.

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?

Schema coverage is 100%, so the schema already documents all 12 parameters in detail. The description mentions the core inputs (word timeline and speaker palette) and some processing behavior, but adds no parameter-level syntax or constraints beyond the schema.

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?

The description uses a specific verb and resource: it plans stacked, speaker-colored reaction captions from a word timeline and speaker palette. It distinguishes itself from mutation or caption-building siblings by stating the local-only planning scope.

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?

The description makes clear this is a local planning step that never changes Premiere, which helps separate it from apply/build tools. However, it does not name explicit alternatives or when-not-to-use conditions.

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