Skip to main content
Glama

Detect Active Picture Bounds

detect_active_picture_bounds

Detect probable letterbox or pillarbox bars in decoded video by finding the recurring active-picture crop rectangle, without modifying the source file.

Instructions

Detect the most frequent active-picture crop rectangle in decoded video, exposing probable letterbox or pillarbox bars without modifying the source.

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": {
      "media_path": "<media_path>"
    },
    "name": "detect_active_picture_bounds"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoCropdetect black threshold from 0 through 255 (default: 24)
use_cacheNoOpt in to bounded process-memory caching keyed by source path/identity, media content SHA-256, exact options, revision, and analysis version. Files over 256 MiB analyze uncached. Default false.
media_pathYesExisting local video file
sample_secondsNoDecode sample duration from 1 through 300 seconds (default: 30)
idempotency_keyNoOptional 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.
analysis_revisionNoOptional project/timeline revision to isolate otherwise-identical analysis inputs.
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

A3.5/5.0
Behavior3/5

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

The description adds real behavior beyond the annotations by disclosing that detection works on a decoded sample and that the source is left untouched. However, the annotations declare readOnlyHint=false, and the description's 'without modifying the source' only scopes to the media file, leaving the agent without clarity on what non-read-only state (cache, session keys) the call touches. No mention of cost, decode time, or failure modes for unreadable files.

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 that names the operation, the object it finds, and the non-destructive guarantee. No filler, no restatement of the title.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the schema documents all eight parameters. What is missing is context proportionate to the tool's complexity: the heavy CEP/expected_* guard and idempotency_key machinery sit in the schema of what appears to be a read-only analysis call, and the description never tells the agent these are optional and typically omitted.

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 every one of the eight parameters is already documented in the schema, including the cropdetect threshold, sample duration, and cache opt-in. The description contributes no parameter-level meaning (no defaults, no guidance on sample_seconds tradeoffs, no note that the guard/idempotency parameters are largely irrelevant to a detection call), so baseline 3 applies.

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?

States a precise verb+resource: detecting the most frequent active-picture crop rectangle in decoded video, specifically for letterbox/pillarbox bars. That is unambiguous and clearly different from sibling detectors (scene edits, silence, beats). It stops short of naming any sibling to route against, which keeps it at 4 rather than 5.

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: an agent can infer this is the pre-crop inspection step because the description frames the output as 'probable letterbox or pillarbox bars'. There is no explicit when-to-use, no prerequisite (e.g. media must be decodable locally), and no statement of when not to call it.

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