ChatCut

multicam_sync

Align ordinary audio/video timeline items from different cameras recording the same take. Uses their shared audio or source timing; unrelated B-roll cannot produce confident alignment. A cutaway spanning an edit in the reference must be split first.

Web execution accepts 2-16 items and requires the full timelineId and, for external callers, projectId. Internal agents use their authorized project when projectId is omitted. The authenticated browser can work while Home or another project/timeline is visible. Navigation never retargets an accepted job; local media stays on the selected browser profile. Desktop uses its local renderer.

The existing alignment engine computes a plan from a captured snapshot and applies only validated ordinary-item positions/tracks. Concurrent edits reject the stale plan. It does not retrim sources or create compound clips. Returns status, changed, alignmentEvidence and actual placementEvidence. Pass itemIds (full IDs or unambiguous prefixes); referenceItemId optionally anchors one of them. Long clips may require splitting to stay within the bounded analysis window. No automatic cloud fallback.

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": {
      "itemIds": "<itemIds>"
    },
    "name": "multicam_sync"
  }
}

Input Schema

Name	Required	Description
`itemIds`	Yes	Two or more timeline item ids (full or prefix) of the angle clips to align.
`projectId`	No	Full project UUID. Required for external browser work; internal agents may omit. Execution/explicit-timeline calls never change later calls' target.
`timelineId`	No	Full target timeline UUID. Required for Web execution; never changes the visible timeline.
`idempotencyKey`	No	Stable key for this browser execution. Reuse only with identical scope and parameters after a lost acknowledgement; applies only to this call.
`referenceItemId`	No	Optional anchor item id; omit to let the engine pick the reference.
`browserProfileId`	No	Optional browser profile override. Omit to select automatically; do not ask the user to choose.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses that a plan is computed from a captured snapshot, that only validated ordinary-item positions/tracks are applied, that concurrent edits reject the stale plan, that sources are not retrimmed and compound clips are not created, and that there is no automatic cloud fallback. Environment-specific behavior (web 2-16 items and required timelineId vs. desktop local renderer, browser profile media locality, navigation never retargeting an accepted job) is exactly the context 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?

Front-loaded with purpose and constraints, and nearly every sentence carries distinct information (eligibility, execution target, snapshot/validation semantics, return fields). It is dense and runs long across four blocks, but the density is informational rather than redundant.

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?

No output schema exists, yet the description enumerates the returned fields (status, changed, alignmentEvidence, actual placementEvidence). Combined with execution-environment rules, failure modes (stale plan rejection, no cloud fallback), and item-count limits, an agent has enough to call this correctly without probing.

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 coverage is 100%, so the baseline is 3. The description does add some value the schema lacks — a 2-16 item bound where the schema only declares minItems 2, the itemIds 'full IDs or unambiguous prefixes' affordance, and the internal-agent projectId omission rule — but most of this duplicates or lightly restates schema 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?

Opens with a specific verb+resource+scope: 'Align ordinary audio/video timeline items from different cameras recording the same take.' This immediately separates it from split_item, edit_item, or preview_timeline-style siblings by naming the multi-camera alignment job explicitly.

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?

Gives clear applicability conditions: items need shared audio or source timing, unrelated B-roll cannot align, and a cutaway spanning an edit in the reference must be split first (implicitly routing to split_item). Also notes long clips may need splitting to fit the analysis window. It does not name a sibling alternative for the single-camera or no-shared-audio case, so it stops short of full when/when-not routing.

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

All ChatCut 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.