Skip to main content
Glama

Vidova

by ai.vidova
OverviewDiscussionsAdmin

Fix a frame of an object track

edit_track
Idempotent

Fix one frame of an object track and carry the fix to its neighbours, without running the tracker again. Give the frame's corners, its box, or only the corners that are wrong (points), in any space: pass corners read off a preview with space preview and its previewId as they are. How the fix is carried: each corner's move at the fixed frame, in source pixels, is added to the same corner on the frames around it times a weight. The weight is 1 at the fixed frame and falls in a straight line to 0 at until, or at the next lost frame, or at the track's end, whichever comes first. propagate says which way it goes. Lost frames are never moved. The fixed frame counts as tracked. Fix the first frame of a flagged range and let the fix fade out where the range ends; for a long drift fix a frame every second or so. The answer ends with the track's new quality verdict and flagged ranges, and a preview_range call with overlays ["tracks"] that shows the changed frames on the film: run it to check. Free.

Input Schema

NameRequiredDescriptionDefault
atYesThe second of the frame to fix (atSpace says what it is). With space preview the preview's own time is used.
boxYes[x0, y0, x1, y1] with x1 > x0 and y1 > y0. A box track takes it as it is; a plane track's corners are moved and scaled so the box around them is this box. null when you pass corners or points.
spaceYesThe space of this call's coordinates. null or source: pixels of the asset file. preview: pixels of a preview image you were shown, with previewId; its time is that preview's time. film: scene pixels from the frame's centre; film_norm: 0 to 1 of the frame; clip: the clip's own picture (with clipId). The tool converts them to the asset's pixels through the film's real transforms.
untilYesThe second where the carried fix fades to nothing (atSpace says what it is). With both, the same distance is used on each side of at. null: it fades out at the next lost frame, or at the track's end.
clipIdYesThe film clip that plays this asset, when space or atSpace needs one and several clips play it. null picks the clip that shows the asset at that time.
pointsYesSome corners only, each named: e.g. [{corner: "top right", point: [612, 140]}] when the quality check says the top right corner drifts. The other corners stay. null when you pass corners or box.
atSpaceYesWhat this call's times are. null or source: seconds into the asset file. timeline: seconds of the film, read through the clip that plays the asset then (clipId to pick one).
cornersYesThe frame's four corners in order top left, top right, bottom right, bottom left. On a box track the box around them is kept. null when you pass box or points.
trackIdYesThe object track id, as the tracking tool printed it or search_assets lists it (objectTracks).
previewIdYesWith space preview or preview_norm: the previewId the preview_frame, preview_range or preview_timeline answer printed. Else null.
projectIdYesThe project this call runs on without changing the open project. null (or leaving it out) uses the open project. wait_for_jobs takes the projectId of the calls that started the jobs.
propagateYesWhere the fix is carried: none (this frame only), forward, backward, or both (null).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

The description adds substantial behavior beyond the annotations: it explains how corner movement is weighted and propagated, how lost frames are handled, that the fixed frame becomes tracked, what the answer ends with, and that a preview_range check should be run. This is exactly the kind of operational detail an agent needs for a mutation tool.

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 purpose is front-loaded in the first sentence and the rest is relevant. It is dense and somewhat long, but the complexity of the propagation model and the coordinate handling justify most of the length.

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?

Given twelve required parameters, no output schema, and non-trivial propagation behavior, the description is complete enough to call the tool correctly. It explains the core mechanics, expected result, and how to verify the outcome with preview_range.

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 baseline is 3. The description nevertheless adds practical parameter meaning by explaining how corners, box, and points are used together, how preview-space coordinates should be passed with previewId, and how propagate and until control the carried fix.

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 states a specific verb and resource: fix one frame of an object track and carry the fix to neighbours without rerunning the tracker. This clearly distinguishes it from tracking tools such as track_points, track_box, or smooth_track.

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

Usage Guidelines4/5

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

It gives clear usage context: pass corners, box, or only wrong points, in any coordinate space, and fix the first frame of a flagged range before letting the correction fade. It also tells the agent to check the result with preview_range. It stops short of explicitly comparing when to use this versus offset_track or smooth_track, so it is not a full 5.

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

All Vidova toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources