Skip to main content
Glama

extract_vertical_clip

Cut a 9:16 vertical clip from any prior video job (find_clips, summarize, or video transcribe), suitable for direct upload to TikTok, Instagram Reels, or YouTube Shorts. Default output is 1080×1920 H.264 / AAC .mp4 with center-cropped framing; audio loudness-normalized to -14 LUFS / -1.5 dBTP for short-form social. Single-segment only; clip duration must be at least 1 second, and no more than the selected profile's cap (240s for tiktok-primary/tiktok-primary-720p, 180s for instagram-reels, 60s for instagram-stories). Operates on a parent job — possessing the parent source_job_id is the capability, no upload step. Two-call flow: (1) call with source_job_id + start + end (in source seconds) to receive {job_id, payment_challenge}; (2) pay via MPP and call with job_id + payment_credential to start processing. Poll get_job_status(job_id) for completion; output is role clip-vertical-video (the .mp4). Flat price: $0.50 per clip. Payment: pay by credit card via the Stripe Checkout link (open the returned payment_url in any browser) or Tempo USDC via mppx. Optional profile parameter selects the encoding profile (default tiktok-primary). Allowed values: tiktok-primary (1080×1920, fast preset, CRF 22), tiktok-primary-720p (720×1280, CBR 3 Mbps — half-resolution mobile-optimized, ~40% faster wall time), instagram-reels (1080×1920, slow preset, CBR 4 Mbps), instagram-stories (same encode shape as instagram-reels). All four profiles loudness-normalize identically. Optional subject parameter controls reframing (default center, preserves today's behavior): auto locks onto the longest-tracked face from the parent's subjects-sidecar (or runs inline detection if the parent has none); subject_id (with subject_id param naming a face_N from the sidecar) locks onto a specific subject; follow switches crop between active speakers across the clip using the sidecar's active_speaker_timeline; manual accepts caller-supplied framing via subject_box: {x, y, w, h} (source pixels) or subject_x_offset (direct crop x). Sidecar shape at /.well-known/weftly-subjects-v1.schema.json. auto/subject_id/follow fall back to center if detection or sidecar resolution fails — the paid job always delivers a clip. Source must be a horizontal video (wider than 9:16) — already-vertical or square sources are rejected. Source must still be in storage (72h TTL for find_clips parents, 24h elsewhere — check expires_at from get_job_status on the parent). Pair with find_clips ($2.00/video) to pick a moment first, then call this to get a download-ready vertical mp4 in under 5 minutes. Multiple extract_vertical_clip calls against one parent are independent paid jobs. Failed jobs auto-refund.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNoSource-relative end time in seconds (must be > start; end - start must be at least 1s, and no more than the selected profile's cap — 240s for tiktok-primary/tiktok-primary-720p, 180s for instagram-reels, 60s for instagram-stories). Required on the first call.
startNoSource-relative start time in seconds. Required on the first call.
t_refNoFor subject="manual" with subject_box — source-seconds timestamp the box applies to. Informational in v1.
titleNoOptional title for the assembled clip. Surfaces in get_job_status and download filenames; doesn't affect the cut itself.
job_idNoJob ID returned from a previous extract_vertical_clip call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.
profileNoOptional encoding profile. Default: tiktok-primary (1080×1920 H.264 fast preset, CRF 22, 6 Mbps cap). tiktok-primary-720p: 720×1280, CBR 3 Mbps — half-resolution mobile-optimized, ~40% faster wall time. instagram-reels: 1080×1920 H.264 slow preset, CBR 4 Mbps. instagram-stories: same encode shape as instagram-reels. All four apply loudness normalization to -14 LUFS / -1.5 dBTP.
subjectNoOptional reframing strategy. Default: "center" (hardcoded center crop, today's behavior). "auto": lock onto the longest-tracked face from the parent find_clips job's subjects-sidecar (or run inline detection if no sidecar). "subject_id": lock onto a specific face named in the sidecar (pass subject_id). "follow": switch crop between active speakers across the clip using the sidecar's active_speaker_timeline (per-segment encode + concat). "manual": caller specifies the subject (pass subject_box or subject_x_offset). See /.well-known/weftly-subjects-v1.schema.json. auto/subject_id/follow fall back to center if detection fails — the paid job always delivers a clip.
subject_idNoRequired when subject="subject_id". Subject id from the parent's subjects-sidecar (e.g. "face_0").
subject_boxNoFor subject="manual" — bounding box of the subject in source pixels. Crop centers on the box center.
source_job_idNoJob ID of any prior video job (find_clips, summarize, or video transcribe). Possessing this id is the capability — extract_vertical_clip is not session-bound, so a user can come back from a different session within the parent's TTL and still extract. Required on the first call.
subject_x_offsetNoFor subject="manual" — direct crop x-offset in source pixels (alternative to subject_box).
payment_credentialNoMPP payment credential (full Authorization header value, e.g. "Payment eyJ..."). extract_vertical_clip accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses payment flow, refund on failure, fallback to center crop when detection fails, output role and encoding details, and the fact that possessing source_job_id is the capability. All behavioral traits are explicit and non-contradictory.

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?

The description is long but densely information-packed. It's logically structured: purpose, flow, constraints, profiles, subject options, and payment details. Every sentence adds necessary context for a tool with 12 parameters and a complex payment handshake; no redundancy. The length is justified, though it could be slightly tightened without losing value.

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?

Even without an output schema, the description explains the output role ('clip-vertical-video'), how to poll for completion (get_job_status), the TTL and refund behavior, and the payment mechanism. Given the tool's complexity, nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 100% schema coverage, the description adds critical meaning beyond the schema: it explains the two-call sequence and which parameters belong to each call, elaborates on profile encoding specifics, details subject-reframing strategies and their fallback, and clarifies the capability nature of source_job_id. This enriches parameter usage far beyond the schema for each of the 12 parameters.

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 opens with a specific verb and resource: 'Cut a 9:16 vertical clip from any prior video job' and names the target platforms (TikTok, Reels, Shorts). It clearly distinguishes itself from siblings like extract_clip and clips_horizontal by focusing on vertical social-media-ready output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It spells out the exact two-call flow (source_job_id + start + end, then job_id + payment_credential), pairs with find_clips, lists hard constraints (single-segment, duration caps per profile, source must be horizontal, TTL), and explains fallback behavior for subject reframing. This leaves no ambiguity about when and how to use it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation4/5

Most tools target distinct tasks (transcribe vs. summarize vs. find_clips, extract_clip vs. extract_vertical_clip, create vs. trigger YouTube). Some overlap exists because summarize and find_clips both produce transcripts, and publish_to_youtube and trigger_youtube_publish are sequential steps that could be confused, but descriptions clarify the boundaries well.

Naming Consistency4/5

The majority follow a verb_noun pattern (complete_upload, extract_clip, find_clips, get_job_status), with a few deviations like the bare verbs 'summarize' and 'transcribe', and 'publish_to_youtube' using a preposition. The pattern is still predictable and readable overall.

Tool Count5/5

11 tools is a well-scoped number for a video/audio processing service covering transcription, summarization, clip extraction, YouTube publishing, and payment testing. Each tool has a clear place, and the count is within the ideal range.

Completeness5/5

The tool surface covers the full lifecycle: job creation (transcribe/summarize/find_clips), payment (mpp_smoke_test, payment challenge flows), upload (complete_upload), status polling (get_job_status), clip extraction (two variants), and YouTube publishing (create/publish/status). No critical gaps are apparent for the stated domain.

Resources