filmcraft-edit

Overview Schema Source Related Servers Discussions Admin

export_frames

Read-only

Export still frames from a source item or Program timeline to a folder at given times or every N seconds, so you can review footage or edit decisions.

Instructions

Export stills to look at footage or the edit: from a source item (to pick moments) or the Program. Give times, or every N seconds over a range.

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": {
      "dir": "<dir>"
    },
    "name": "export_frames"
  }
}

Input Schema

Name	Required	Description	Default
`dir`	Yes	Folder to write the frames to
`end`	No	End of the range for `every` (default: the item's or sequence's duration)
`item`	No	Source item id; omit for the Program (the edit)
`every`	No	Instead of times: one frame every N seconds
`start`	No
`times`	No	Seconds (source time for an item, timeline time for the Program)
`format`	No		jpeg
`project`	No	Path to the .fcproj project file; omit to edit the FilmCraft app connected with connect_app

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 7, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Beyond the annotations the description adds the meaningful behavioral distinction that omitting an item exports from the Program timeline and that time values are interpreted in source time vs timeline time. It does not disclose that files are actually written to disk (which sits in some tension with readOnlyHint=true), nor output file naming, overwrite behavior, or how many frames a broad every-range could produce.

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 short sentences, front-loaded with the action and capture source, then the sampling options. No filler; every clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter export tool with no output schema, the description leaves notable gaps: it does not say what is returned (paths, count, or nothing), how frames are named, or whether times and every may be combined. The essential selection semantics are present, but the post-invocation picture is incomplete.

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?

With 75% schema coverage the schema already documents dir, item, every, end, times, and project. The description still adds real meaning: it establishes that times and every are alternative sampling strategies and that start/end scope the every mode, which is not stated in the schema for start or format.

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?

States a concrete verb+resource ('Export stills') and immediately scopes it to two capture sources: a source item for picking moments, or the Program (the edit). That two-mode framing lets an agent distinguish it from export_timeline and render, though it never names those siblings explicitly and leaves 'Program' as unexplained domain jargon.

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

Usage Guidelines3/5

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

The phrase 'to look at footage or the edit' gives a use context, and 'Give times, or every N seconds over a range' steers between the two sampling modes. It offers no explicit when-not guidance and never contrasts with render_frame, render, or export_timeline, so the agent must infer that this is the multi-frame sampling tool rather than a single-frame or video-render tool.

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