Mark Studios Video Toolkit

Create a video editing brief

create_editing_brief

Read-onlyIdempotent

Builds a filled-in 7-section video editing brief (project, audience and goal, references, must-include moments, brand rules, deliverable specs, timeline) from whatever the user already knows, and lists the gaps an editor will ask about. Use when someone is about to hand footage to an editor, freelancer or agency. Pass only fields you know.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_editing_brief"
  }
}

Input Schema

Name	Required	Description
`copy`	No	What to copy: Pacing, captions, color, music, graphics
`kill`	No	KILL: Anything that can't be used
`must`	No	MUST: Timestamps from the raw footage that have to land
`nice`	No	NICE-TO-HAVE: Moments to use if they fit
`avoid`	No	What not to copy: The traps to avoid
`donts`	No	Don'ts: Past mistakes not to repeat
`music`	No	Music rules: Which library or tracks are licensed
`master`	No	Master: Resolution, frame rate, audio level
`metric`	No	The one metric: What success means for this video
`channel`	No	Channel or brand: Where it will be published
`feeling`	No	How viewers should feel: The reaction you want at the end
`sponsor`	No	Sponsor read: Where it goes, if any
`approver`	No	Approver: Exactly one person
`audience`	No	Who it's for: One sentence
`captions`	No	Captions: Burned in, SRT file, or both
`delivery`	No	Delivery: Where final files go
`final_due`	No	Final due: Date and time
`sensitive`	No	SENSITIVE: Faces to blur, legal or private material
`references`	No	2–4 reference videos: Links with timestamps
`brand_files`	No	Brand files: Lower-thirds, intro, outro, logo
`short_clips`	No	Short clips: Number, ratio and length
`fonts_colors`	No	Fonts and colors: Font names and HEX codes
`publish_date`	No	Publish date: Date and time, not just a day
`length_target`	No	Length target: A target with a hard floor and ceiling
`response_time`	No	Response time: How fast you reply to a cut
`rough_cut_due`	No	Rough cut due: Date and time
`working_title`	No	Working title: The title you plan to publish, or the top two options
`revision_rounds`	No	Revision rounds: How many, in writing
`footage_location`	No	Footage location: The folder link and what's in it
`thumbnail_frames`	No	Thumbnail frames: Frames to export as stills

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real value on top: it discloses that the tool fills gaps from partial input and returns a list of gaps an editor will ask about. It stops short of saying whether anything is persisted or in what format the brief is returned, which matters given there is no output schema.

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?

Two sentences, front-loaded with what is produced, followed by the usage condition. Every clause carries information; nothing is repeated from the schema or title.

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 30-parameter, all-optional tool with no output schema, the description covers what is generated, what happens with missing inputs, and when to invoke it. The remaining gap is the shape/format of the returned brief and gap list, which an agent would otherwise have to discover by calling.

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 each of the 30 optional parameters has a descriptive label plus guidance (e.g. 'KILL: Anything that can't be used', 'Approver: Exactly one person'), so the schema carries parameter meaning. The description adds only the general rule 'Pass only fields you know' and no field-level semantics, which is the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and artifact ('Builds a filled-in 7-section video editing brief') and enumerates the seven sections, so the agent knows exactly what will be produced. It does not explicitly route away from siblings like start_video_project or get_platform_video_specs, but the artifact is unambiguous enough that confusion is unlikely.

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?

'Use when someone is about to hand footage to an editor, freelancer or agency' gives a clear triggering situation, and 'Pass only fields you know' tells the agent partial input is acceptable. No exclusions or named alternatives are provided, which keeps it short of a 5.

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

All Mark Studios Video Toolkit 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.

Resources

Need Help?