Skip to main content
Glama

Plan each place's crop

plan_reframe
Destructive

Plans per-platform video crops before rendering by finding shots and following motion, writing crop.json and preview sheets for review or adjustment.

Instructions

Use it when the user wants to see a video's crop for each place before it renders. Plans what reframe_video renders, without rendering: finds the shots of a finished video and, for each place's shape, a window that follows what moves in each shot, or a padded shot where a crop would cut too much. Writes crop.json, every shot with its window for each shape, sheet.png, each shape's window drawn on every shot's frames (a solid outline for a crop, a dashed one for a padded shot), with more shots in sheet-2.png and on, and FORMATS.md, which the result shows with the command that renders the plan. Look at the sheet, move a window that misses in crop.json, then give that crop.json to reframe_video as crop. A plan in a folder of an earlier render keeps its files. For the files themselves in one job, use reframe_video instead. The reframe playbook (makersmcp_playbook) has the whole job. (reframekit 0.1.3, on this machine.)

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": {
      "video": "<video>"
    },
    "name": "plan_reframe"
  }
}

Input Schema

NameRequiredDescriptionDefault
forNoThe places to plan for, in one run at most 12: any of tiktok, reels, shorts, youtube, x, linkedin, feed, square, all (the default) or a size like 1080x1350, as reframe_video takes them.
fpsNoThe files' frame rate (default: the video's own), for the render command the plan gives.
padNoWhat a padded shot sits on: blur (default), black, white, a color like #0f172a, or brand, which needs brand. The render command the plan gives carries it.
cropNoAn edited crop.json whose shapes to keep: the plan adds the windows of a place whose shape it has none of. It takes no cuts or steps, and no mode but fit.
cutsNoEvery shot change, in place of those found: seconds like 3.2,7.5, or a JSON file of seconds, of frames with their fps, a launch film's film.timeline.json or a demo's steps.json.
lufsNoThe loudness the files will have in LUFS (default -14), for the render command the plan gives.
modeNofollow crops each shot where what moves is, and pads a shot a crop would cut (default follow); center crops from the middle; pad shows every shot whole; fit keeps the picture's own shape.
trimNoSet to false never to cut a file to its place's length. The render command the plan gives carries it.
brandNoA brand kit, its folder, brand.json or _brand.yml, for padded shots on its page background color. make_brand_kit makes one.
coverNoThe moment each place's cover shows, in seconds like "4.5" (default: picked).
stepsNoThe steps.json of the demo this video is, when it is not beside the video under its name.
videoYesThe finished video, any file ffmpeg reads, like film.mp4 from a launch film or demo.mp4 from a demo. The film.timeline.json or steps.json beside it, under its name, gives its shots.
out_dirNoFolder to save into, absolute or relative to /app. Default: <video-folder>/reframekit-<video-name>, where <video-name> is the name of video without its extension and <video-folder> is the folder video is in. A run replaces the files an earlier run of this kit left there, so give each version its own out_dir.
secondsNoKeep at most this long in each place's video, cut at a shot change: seconds like "30", or "1:30". The render command the plan gives carries it.
wait_secondsNoHow long to wait for the result, counted from the start of the call, before returning a job_id to wait on. Some clients end a call after 60 or 240 seconds; 45 is safe in all of them.

Output Schema

NameRequiredDescriptionDefault
kitYes
docsNoThe notes the text shows, and where each one is.
nextNoWhat to do next, as the Next line says.
toolYes
filesNo
folderNoWhere the kit saved its files.
job_idYes
passedNoFor checks: whether the check passed.
statusYes
continuedNoTrue when this call continued the job of an identical call whose answer did not reach the client, instead of starting another.
exit_codeNo
last_lineNoWhat the kit was doing last.
expires_atNoWhen the download links stop working.
next_actionNo
elapsed_secondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.3/5.0
Behavior4/5

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

Goes well past the annotations by disclosing that nothing is rendered, the exact file set written, the solid-vs-dashed outline convention, the sheet-2.png overflow, and that a plan placed in an earlier render's folder keeps that render's files. The one behavior carried only by the schema rather than the description is that a run replaces files left by an earlier run in out_dir, which is the very thing destructiveHint=true warns about.

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?

Front-loads the when-to-use clause and then the what-it-does clause, and every sentence carries information (outputs, review loop, alternative, playbook). It is dense and runs the file inventory into one long sentence, which costs some readability, but little is redundant.

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 a 15-parameter, file-producing tool with an output schema, the description covers purpose, workflow, outputs, and the sibling boundary well. The remaining gap is the overwrite/replace behavior of out_dir, which an agent would only learn from the schema field rather than the prose.

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% and the 15 parameter descriptions are themselves detailed (for, pad, crop, cuts, mode, out_dir), so the baseline is 3. The description adds only indirect meaning — 'for each place's shape' maps to `for`, and 'give that crop.json to reframe_video as crop' explains the `crop` input — without adding syntax or defaults of its own.

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 and resource — plans each place's crop without rendering — and names the exact artifacts it produces (crop.json, sheet.png, sheet-2.png, FORMATS.md). It also explicitly distinguishes itself from the sibling: 'For the files themselves in one job, use reframe_video instead.'

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?

Opens with the triggering condition ('when the user wants to see a video's crop for each place before it renders'), names the alternative (reframe_video) and the boundary between them, and points to makersmcp_playbook for the full job. It even describes the follow-up loop: inspect the sheet, edit crop.json, hand it to reframe_video as crop.

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