Skip to main content
Glama
tydude001

proofcut

by tydude001
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

seed_timeline

DestructiveIdempotent

Create or replace a project timeline from a clip, cutting silences automatically with auto-editor. Preserves the previous timeline for undo.

Instructions

Lay a clip down as the timeline, silence-cut by auto-editor by default.

edit_expr passes auto-editor's edit language straight through, e.g. "(or audio:0.03 motion:0.06)".

Writes project.otio and replaces any timeline already there — every cut made since the last seed included. It seeds a project rather than re-cutting one, and a re-seed with the same arguments lands the same timeline. The old one is snapshotted first, so undo puts it back.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNoThe project directory to act on. Omit it — the usual case — when this server is bound to a project (started as `proofcut -C DIR mcp`, or inside a project; `ping` says which): it then resolves to that one bound project, a relative path resolves against it, and a path outside it is refused by name. Unbound, `path` is the whole address and omitting it refuses rather than guessing.
marginNoHow much to leave either side of kept audio, in auto-editor's own notation (e.g. `0.2s`), so an edge lands in the silence rather than on the breath.
clip_idYesThe clip to lay down as the timeline.
edit_exprNoauto-editor's edit language, passed straight through — e.g. `(or audio:0.03 motion:0.06)`. It replaces the threshold-based rule.
thresholdNoauto-editor's audio loudness threshold, 0–1. Lower keeps quieter material.
remove_silencesNoSilence-cut the clip on the way in, through auto-editor. On by default; false lays the whole clip down untouched.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed19 schema fields changedv0.25.0
    • addedInput schema / properties / clip_id / description
      Added value: +"The clip to lay down as the timeline."
    • removedInput schema / properties / clip_id / title
      Removed value: -"Clip Id"
    • removedInput schema / properties / edit_expr / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedInput schema / properties / edit_expr / description
      Added value: +"auto-editor's edit language, passed straight through — e.g. `(or audio:0.03 motion:0.06)`. It replaces the threshold-based rule."
    • removedInput schema / properties / edit_expr / title
      Removed value: -"Edit Expr"
    • addedInput schema / properties / edit_expr / type
      Added value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / margin / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedInput schema / properties / margin / description
      Added value: +"How much to leave either side of kept audio, in auto-editor's own notation (e.g. `0.2s`), so an edge lands in the silence rather than on the breath."
    • removedInput schema / properties / margin / title
      Removed value: -"Margin"
    • addedInput schema / properties / margin / type
      Added value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / path / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedInput schema / properties / path / description
      Added value: +"The project directory to act on. Omit it — the usual case — when this server is bound to a project (started as `proofcut -C DIR mcp`, or inside a project; `ping` says which): it then resolves to that one bound project, a relative path resolves against it, and a path outside it is refused by name. Unbound, `path` is the whole address and omitting it refuses rather than guessing."
    • removedInput schema / properties / path / title
      Removed value: -"Path"
    • addedInput schema / properties / path / type
      Added value: +[
+  "string",
+  "null"
+]
    • addedInput schema / properties / remove_silences / description
      Added value: +"Silence-cut the clip on the way in, through auto-editor. On by default; false lays the whole clip down untouched."
    • removedInput schema / properties / remove_silences / title
      Removed value: -"Remove Silences"
    • addedInput schema / properties / threshold / description
      Added value: +"auto-editor's audio loudness threshold, 0–1. Lower keeps quieter material."
    • removedInput schema / properties / threshold / title
      Removed value: -"Threshold"
    • removedInput schema / title
      Removed value: -"seed_timelineArguments"
  2. First observedv0.24.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description builds on these by explaining exactly what gets destroyed ('replaces any timeline already there, every cut made since the last seed included') and how recovery works ('snapshotted first, so undo puts it back'). It also confirms idempotence ('a re-seed with the same arguments lands the same timeline'). This adds genuine context beyond the structured hints, though it doesn't contradict them.

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?

Four sentences with the core action front-loaded in the first line, followed by the edit_expr usage, then side effects. No filler or redundant restatement of the name; every sentence earns its place and the most important behavioral warnings appear early.

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?

Given an output schema exists, return values need no description. With 100% schema coverage on six parameters and rich behavioral notes on the destructive/idempotent nature, the description is complete for an agent deciding whether and how to call it. Only minor omissions, such as explicit permission requirements, keep it from a 5.

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%, so the baseline is 3. The description reinforces edit_expr ('passes auto-editor's edit language straight through') with an example and clarifies margin's purpose, but it largely echoes what the schema already documents. It adds modest value rather than compensating for gaps, so 3 is appropriate.

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-plus-resource statement: 'Lay a clip down as the timeline, silence-cut by auto-editor by default.' It also distinguishes itself from the cut_by_* and timeline_* siblings by framing the action as seeding a project rather than re-cutting one, so an agent can tell it apart without opening the 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?

Gives an explicit when-not: 'It seeds a project rather than re-cutting one,' which separates it from cut_by_transcript/cut_by_time. It also warns it replaces any existing timeline, which sets expectations about when a call is appropriate. It does not name specific sibling alternatives, but the exclusion is concrete enough.

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

Deploy Server

Other Tools