premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Verify Temporal Render Artifact

verify_temporal_render_artifact

Read-onlyIdempotent

Validates a short exported video against expected RGB and audio samples at multiple times, rejecting stills or mismatched artifacts and recording hashes and host provenance.

Instructions

Validate actual short exported video at 2–32 times with decoded RGB tolerances and optional decoded-audio RMS windows. Rejects stills and mismatched samples; records fixture/artifact hashes and explicit declared host provenance. This sampled harness does not prove all frames, Undo/reopen, playback, glyphs or destination compatibility.

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": {
      "path": "<path>",
      "fixture_id": "<fixture_id>",
      "fixture_sha256": "<fixture_sha256>",
      "duration_seconds": "<duration_seconds>",
      "samples": "<samples>"
    },
    "name": "verify_temporal_render_artifact"
  }
}

Input Schema

Name	Required	Description
`host`	No	Optional caller-declared licensed-host provenance; artifact analysis cannot authenticate these values.
`path`	Yes	Absolute existing caller-selected video artifact (maximum 1 GiB, expected duration at most 60 seconds).
`samples`	Yes	Expected temporal image checks; choose times around transitions and interpolation, with compression-aware tolerances.
`fixture_id`	Yes	Opaque fixture ID.
`audio_samples`	No	Optional actual decoded-audio energy checks; analysis downmixes to mono 48kHz and cannot prove multichannel routing.
`fixture_sha256`	Yes	Lowercase SHA-256 of generated fixture/input definition.
`idempotency_key`	No	Optional client-chosen key (1-128 chars of A-Z a-z 0-9 . _ : -) for this intended edit. Pass a fresh key per edit and reuse it only when retrying that same edit, for example after a client-side timeout. A repeat with the same tool, key and arguments is not run again: while the first call is running it fails with IDEMPOTENCY_IN_PROGRESS (poll get_last_operations); after it finished it returns the original outcome marked replayed. A definite failure with nothing applied (receipt outcome not_applied) may be retried with the same key. Reusing a key with different arguments fails with IDEMPOTENCY_KEY_REUSED. Scoped to this MCP session (the stdio server process, or the HTTP server process when Streamable HTTP is stateless per request) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated.
`duration_seconds`	Yes	Expected actual video duration.
`expected_cep_target`	No	Optional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
`expected_project_path`	No	Optional 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.
`duration_tolerance_seconds`	No	Allowed duration deviation, default 0.05 seconds.

Output Schema

Name	Required	Description
`ok`	Yes	Whether the tool completed successfully.
`data`	No	Tool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it.
`tool`	Yes	The registered MCP tool name.
`error`	No	Failure detail when ok is false.
`receipt`	No	Versioned common mutation receipt; success never implies rendered verification.
`idempotency`	No	Present 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.

First observedv1.30.0Nov 14, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real behavioral context: it is a sampled harness that does not prove all frames, Undo/reopen, playback, glyphs, or destination compatibility, and it records fixture/artifact hashes plus caller-declared host provenance that 'cannot authenticate these values.' That is exactly the kind of scope-of-proof disclosure an agent needs to judge whether the result is sufficient evidence.

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

Conciseness4/5

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

Two sentences, both front-loaded: capability first, then the negative scope that constrains trust in the result. No filler, though the phrasing is dense and jargon-heavy, which costs a little readability against a 5.

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 11-parameter tool with nested sample/host objects, the description covers what is checked, what is out of scope, and what provenance is recorded; an output schema exists, so return values need not be restated. Gaps are minor: no mention of size/duration limits (1 GiB, 60 s) or the expected_project_path/CEP guards, which the agent only finds in the schema.

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 the per-parameter baseline is 3; the description goes beyond it by explaining the aggregate semantics of the sample set (2–32 samples with compression-aware tolerances, taken around transitions/interpolation) and by framing audio samples as optional RMS window checks. It does not add anything about idempotency_key, duration identity, or the CEP/project guards, which remain schema-only.

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?

Opens with a specific verb and resource ('Validate actual short exported video') plus concrete scope: 2–32 temporal samples, decoded RGB tolerances, optional decoded-audio RMS windows. 'Rejects stills and mismatched samples' further narrows the input class, which implicitly separates it from the still/MOGRT artifact verifiers. It never names a sibling, so differentiation is by implication rather than explicit routing.

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 implied: call this on a real exported video after render, not on a still. The clause 'Rejects stills and mismatched samples' tells the agent which inputs are wrong, but there is no statement of when to prefer this over verify_delivery_file, verify_mogrt_artifact, or export_and_verify, and no prerequisite/cost guidance beyond sample count.

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

Deploy Server