Skip to main content
Glama

Audit Timeline Health

audit_timeline_health
Read-onlyIdempotent

Audit a sequence snapshot for flash frames, gaps, overlaps, disabled clips, repeated shots, missing audio, extreme speed, invalid times, empty tracks, leading/trailing gaps; report 0–100 score/fixes.

Instructions

Audit one sequence snapshot for flash frames, gaps, overlaps, disabled clips, repeated shots, video without audio, extreme speed, invalid times, empty tracks, leading black, and trailing gaps; returns a 0..100 score, findings with timecodes, and fix routes. 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": {
      "snapshot": "<snapshot>"
    },
    "name": "audit_timeline_health"
  }
}

Input Schema

NameRequiredDescriptionDefault
snapshotYesSequence snapshot to audit.
frame_rateNoFrame rate override for frame math and timecodes (1..240). Defaults to the snapshot frame rate or 30.
gap_min_framesNoMinimum gap length in frames to report (default 1).
max_speed_percentNoAbsolute speed above this percentage is flagged (default 400).
expected_cep_targetNoOptional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
expected_frame_rateNoOptional expected frame rate; a mismatch is an error.
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.
flash_frame_max_framesNoClips lasting this many frames or fewer are flagged as flash frames (default 3).
expected_duration_secondsNoOptional target duration; clips past it and trailing gaps before it are flagged.

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

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is mostly covered; the description still adds 'Local-only; never changes Premiere', which clarifies there is no host round-trip. It also discloses the output shape (score plus timecoded findings plus fix routes), though it omits threshold defaults and how the score is aggregated.

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?

A single front-loaded sentence with the verb and object first, followed by the checked conditions and then the return contract. The long enumeration is dense but each item is a distinct audit rule that earns its place.

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?

With annotations, a fully described nested schema and an output schema, the description covers purpose, checks, return contract and the local-only guarantee, which is enough to call it correctly. The remaining gap is that it does not say where the snapshot should come from (get_sequence_structure / inspect_sequence_structure_uxp) despite the schema accepting those raw keys.

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 description coverage is 100%, so defaults and bounds for frame_rate, gap_min_frames, max_speed_percent, flash_frame_max_frames and the expected_* guards are already documented in structured data. The description's mention of flash frames, gaps and extreme speed loosely maps to those knobs but adds no syntax or defaulting behavior beyond the schema, so the baseline 3 applies.

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 ('Audit') and resource ('one sequence snapshot'), then enumerates the exact defects checked (flash frames, gaps, overlaps, disabled clips, repeated shots, video without audio, extreme speed, invalid times, empty tracks, leading black, trailing gaps). It also declares the return payload (0..100 score, findings with timecodes, fix routes), which distinguishes it from narrower siblings like get_timeline_gaps.

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?

The scope 'one sequence snapshot' implies the tool operates on a pre-fetched snapshot rather than a live sequence, and 'Local-only; never changes Premiere' hints at when it is safe to call. However, no sibling is named and no explicit when-to-use/when-not guidance is given, so routing against inspect_timeline_snapshot or get_timeline_gaps is left to inference.

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