cuttingfloor

Set speed

clip.set_speed

Idempotent

Speed up, slow down, ramp or reverse a clip and its linked clips. rate is constant; curve is a speed ramp over the clip. The clip keeps its source and its length changes; ripple (default) moves later clips. Pitch is kept unless preserve_pitch is false. Returns the edit result (see the server instructions).

Input Schema

Name	Required	Description	Default
`rate`	No	Constant speed: 2 = twice as fast
`curve`	No	Speed ramp: rates at fractions of the clip as it plays after the change (first at 0, last at 1; 0.5 is halfway through the new length), linear between. timeline.get gives each point its clip frame and source frame
`ripple`	No	Move later clips as the clip gets longer or shorter
`clip_id`	Yes
`preview`	No	inline: image in the result; link: URI that renders on read; none	link
`reverse`	No
`interpolate`	No	Video, when it shows fewer new frames a second than the sequence (slowed, or a lower frame rate; rate 1 smooths that): none repeats frames; blend crossfades neighbours; motion makes new frames from the movement (minterpolate, slow). Made once as a job of its own (job.list); a render that needs it names the job until it is done, and an export waits. Up to 6000 frames a clip
`timeline_id`	Yes	Timeline handle; every edit returns a new one
`other_tracks`	No	What the other tracks do when this edit moves later clips on the clip's own tracks (linked clips always move with it). stay: they don't move, and the result warns which clips there now play early or late. sync: they get the same change, so titles, overlays and sound stay in step: time taken out here comes out of them too (like range.extract), time added here opens the same gap in them (clips crossing that point are split, as insert does). Locked tracks always stay	stay
`preserve_pitch`	No	Keep voices at their pitch (default true)

Output Schema

Name	Required	Description
`parent`	Yes	Timeline handle; every edit returns a new one
`changed`	Yes
`clip_id`	No
`preview`	Yes
`clip_ids`	No
`track_id`	No
`warnings`	Yes
`timeline_id`	Yes	Timeline handle; every edit returns a new one

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / interpolate / description

Previous value: -"Video, when it shows fewer new frames a second than the sequence (slowed, or a lower frame rate; rate 1 smooths that): none repeats frames; blend crossfades neighbours; motion makes new frames from the movement (minterpolate, slow, on first render). Up to 6000 frames a clip"New value: +"Video, when it shows fewer new frames a second than the sequence (slowed, or a lower frame rate; rate 1 smooths that): none repeats frames; blend crossfades neighbours; motion makes new frames from the movement (minterpolate, slow). Made once as a job of its own (job.list); a render that needs it names the job until it is done, and an export waits. Up to 6000 frames a clip"

Changed1 schema field changedNov 1, 2026

addedInput schema / properties / interpolate

Added value: +{
+  "description": "Video, when it shows fewer new frames a second than the sequence (slowed, or a lower frame rate; rate 1 smooths that): none repeats frames; blend crossfades neighbours; motion makes new frames from the movement (minterpolate, slow, on first render). Up to 6000 frames a clip",
+  "enum": [
+    "none",
+    "blend",
+    "motion"
+  ],
+  "type": "string"
+}

First observedOct 25, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds real behavior: the clip keeps its source, its length changes, ripple moves later clips, and pitch is preserved by default – none of which the annotations convey. It is silent on failure cases and how reverse interacts with rate.

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?

Five short sentences, front-loaded with the verbs then the mode distinction, then side effects, then the return note. Every sentence carries information an agent needs and there is no filler.

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?

An output schema exists and the description correctly defers to server instructions for the returned edit result, so the return value need not be spelled out. It covers the mode choice and the ripple and pitch side effects, but leaves reverse semantics and the heavy interpolate job behavior entirely to 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 80%, so the schema already documents most parameters and the baseline is 3. The description still adds meaningful semantics by contrasting rate (constant) with curve (a ramp over the new length) and by stating that preserve_pitch defaults to true. That marginal lift over the schema earns a 4 rather than a 5.

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 concrete verbs (speed up, slow down, ramp, reverse) against a named resource (a clip and its linked clips). That clearly separates it from clip.freeze, clip.trim, clip.slip, and clip.set_animation without the agent opening any schema.

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?

Explains the two mutually exclusive modes – constant rate versus a curve ramp – which is the main in-tool choice. It also tells the agent what ripple and other_tracks do by default, but never states when to prefer a sibling such as clip.freeze or clip.trim instead.

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

All cuttingfloor tools Inspect

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.