aicut

Make a character copy a video's motion

motion_control

Destructive

Takes a picture of a character and a reference video and generates a video of THAT character performing the reference's motion (a dance, a walk, a gesture). Returns the new job's id immediately. WHEN: the user wants their character to dance, copy a move or perform a clip's motion. The clip supplies the MOVEMENT only; the character comes entirely from the picture. CONSENT: a real person's picture only with their permission, never a public figure or celebrity. The reference clip must be 3 to 30 seconds (10 if the character picture is a still portrait) and reasonably large; a clip outside the model's bounds is refused before anything is charged. THE CARD: this call already opened the aicut card: do not call show_generation for this job. WAIT: wait_for_generation (this id, media), again at once while terminal: false, then one short line; no get_* polling, timers, background shells or narrating the wait. No card? Give the user the url. COST: this spends the user's tokens: the reference clip's LENGTH times a per-second rate that depends on model and resolution (a 30-second reference costs ten times a 3-second one). The clip's length is MEASURED BY THE SERVER: that measurement is the price. A clip it cannot measure (a WebM, an unreadable header) is REFUSED uncharged: re-encode to MP4. There is no length argument. An external url costs one media-ingest slot: quote and create from the SAME url to pay it once. SPENDS TOKENS: price with estimate_only: true, ask in the SAME message as the price, and wait for a go that names THIS purchase (SPENDING RULES, this server's instructions). IDEMPOTENCY: a reused idempotency_key REPLAYS the first job whatever the settings: never reuse one for a new generation (this server's instructions).

Input Schema

Name	Required	Description
`model`	Yes	`kling-3.0-motion-control` is the better and about 4x dearer one; `kling-2.6-motion-control` is the everyday choice. Ask the user rather than picking the expensive one for them.
`resolution`	Yes	Output resolution; 1080p costs more per second. REQUIRED: use `720p` unless the user asked for `1080p`, and name the choice in the priced ask; never carried over from an earlier request.
`estimate_only`	No	Price only; creates nothing.
`character_image`	Yes	URL of the picture of the character to animate. A URL from this account's generations or uploads, or a public https URL (imported first); another account's is refused.
`idempotency_key`	No	Retry-safety key (IDEMPOTENCY).
`reference_video`	Yes	URL of the video whose motion to copy. A URL from this account's generations or uploads, or a public https URL (imported first); another account's is refused.
`character_orientation`	No	What the character picture is: `video` (default) for a full-body or moving subject, `image` for a still portrait (which lowers the reference clip's maximum to 10 seconds).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

The description goes well beyond the annotation hints (destructive=true, openWorld=true): it explains the token-cost model (clip length × per-second rate), that the server measures the clip length, that unmeasurable clips are refused uncharged, the 3–30s (10s for portraits) bounds, the consent restriction on real people and celebrities, and the idempotency-key replay semantics. This is exactly the kind of pricing, refusal, and failure behavior the annotations cannot convey.

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 front-loaded with purpose, then WHEN, CONSENT, CARD, WAIT, COST, and IDEMPOTENCY, so it reads as labelled sections rather than prose. It is long and mixes workflow protocol (card and wait narration rules) into a tool description, but nearly every clause carries operational information an agent needs.

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?

There is no output schema, yet the description states the return ('the new job's id immediately'), gives the follow-up protocol, and says what to do when no card is present ('give the user the `url`'). Together with the consent, cost, and refusal rules, an agent can call the tool and handle the result without opening anything else.

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 earns one point above that by clarifying each input: there is no length argument (the server measures it), an external url consumes a media-ingest slot and must be quoted and created from the same url, and the 10-second cap for a still portrait is tied to `character_orientation`. It adds real meaning on top of the enum and property descriptions.

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 first sentence names a specific verb and resource: it generates a video of a character from a picture performing a reference clip's motion. It also sharply separates the inputs ('the clip supplies the MOVEMENT only; the character comes entirely from the picture'), which distinguishes it from siblings like generate_video or edit_video.

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?

An explicit WHEN block gives the trigger ('the user wants their character to dance, copy a move or perform a clip's motion'), and the text also states when NOT to call siblings ('do not call `show_generation`', 'no `get_*` polling') and routes to `wait_for_generation` and `estimate_only: true` instead. The consent and length-precondition rules add further constraints on when to call it.

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

All aicut tools Inspect

Try in Browser