Skip to main content
Glama

Rank Short Form Candidates

rank_short_form_candidates
Read-onlyIdempotent

Ranks long-video transcript windows as short-form clip candidates using explainable local heuristics and overlap suppression, without changing Premiere or predicting virality.

Instructions

Rank long-video transcript windows as short-form clip candidates using explainable local heuristics (hook, completeness, density, supplied evidence peaks, keywords, duration fit, speaker consistency) with overlap suppression. Local-only plan; not a virality prediction and 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>"
    },
    "name": "rank_short_form_candidates"
  }
}

Input Schema

NameRequiredDescriptionDefault
keywordsNoTopic keywords or short phrases whose presence is rewarded.
frame_rateNoFrame rate used to snap start/end frames; defaults to 30.
hook_wordsNoExtra single-word hook tokens added to the built-in lexicon.
max_secondsNoLongest allowed candidate duration in seconds; defaults to 60.
min_secondsNoShortest allowed candidate duration in seconds; defaults to 15.
motion_peaksNoOptional source-time motion peaks from local analysis (for example detect_motion_peaks).
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.
marker_secondsNoOptional source-time editor-flagged moments (markers).
max_candidatesNoMaximum candidates returned after overlap suppression; defaults to 8.
laughter_secondsNoOptional source-time laughter moments supplied by the caller.
audio_energy_peaksNoOptional source-time audio energy peaks from local analysis (for example detect_audio_transients).
expected_cep_targetNoOptional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
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

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this with 'never changes Premiere,' while adding genuinely new context: the ranking is explainable local heuristics, not a virality prediction, with overlap suppression. It stops short of describing return shape, but the output schema covers that.

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 tight sentences: the first defines the operation and its heuristic basis, the second front-loads the critical scope constraints. No filler.

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?

Given 13 parameters, nested objects, and an output schema, the description supplies the essential framing (local-only, heuristic, non-mutating) and hedges against misuse as a virality predictor. The rich schema carries parameter detail, so this is close to complete, though it could clarify how optional evidence inputs affect 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 100%, so baseline is 3; the description adds value by naming the heuristic dimensions that map to parameters (evidence peaks, keywords, duration fit, speaker consistency), helping the agent understand why those inputs matter. It doesn't explain defaults or ranges, which the schema handles.

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 ('rank') and resource ('long-video transcript windows as short-form clip candidates') and enumerates the exact heuristic factors used. An agent can distinguish this planning/ranking tool from sibling analysis and planning tools without opening the schema.

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 clearly scopes usage with 'Local-only plan; not a virality prediction and never changes Premiere,' telling the agent it is a non-mutating heuristic ranker. It doesn't explicitly name alternative siblings (e.g., plan_short_export_folder) or exclusions, so it stops short of full when/when-not routing.

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