Skip to main content
Glama

ws_edit

Edit the project by editing its files — exact old→new replacement, like editing code. job/<job_id>/transcript.txt, transcript/<clip_id>.txt, words/<clip_id>.txt: delete words, phrase lines or pause lines to CUT them from the edit. job/<job_id>/timeline.txt: delete a clip line (remove clip), change its start (move), move the line under another track header (change track), change its src range (trim) or x. project/<project_id>/scenes/<scene_id>/document.html: any edit. Applied as ONE undoable, all-or-nothing batch. dry_run=true returns the operations without applying. keep_tracks_in_sync=true (transcript cuts only): in the same edit, overlays, cutouts, captions, sound effects and music after the cut move with the footage they sat over. old must be copied exactly from a fresh ws_read.

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": {
      "path": "<path>",
      "old": "<old>",
      "new": "<new>"
    },
    "name": "ws_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
newYes
oldYes
pathYes
confirmNo
dry_runNo
replace_allNo
keep_tracks_in_syncNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / keep_tracks_in_sync
      Added value: +{
      +  "default": false,
      +  "title": "Keep Tracks In Sync",
      +  "type": "boolean"
      +}
  2. Added

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations: declares the batch is atomic and undoable as one unit, that dry_run returns operations without applying, and explains the ripple behavior of keep_tracks_in_sync on overlays/captions/music. The undoable all-or-nothing framing is what reconciles the destructive-looking word/pause-line deletions with destructiveHint=false.

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-loads the core mechanic, then organizes the path-specific rules as a compact per-path list rather than prose. It is dense and long, but nearly every clause carries operational information; the only soft spot is the trailing keep_tracks_in_sync paragraph, which is slightly buried.

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 7-parameter mutation tool with no output schema, this covers the important ground: what is editable per file type, atomicity, undo, preview, and sync ripple. The gaps are the undocumented confirm/replace_all semantics and the absence of any statement about the return shape of a dry run or a failed match.

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 0%, so the description must carry all parameter meaning, and it only partially does. It richly explains path, old, new, dry_run and keep_tracks_in_sync, but confirm and replace_all — the two booleans most likely to cause surprise (occurrence scope, gating) — are never mentioned anywhere.

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?

States a specific verb+resource (edit project files) and immediately pins down the mechanism: exact old→new replacement. It then enumerates the concrete path families (transcript, timeline, document.html) with what each one lets you do, so an agent knows precisely what class of operation this covers versus ws_read or ws_grep.

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 strong operational guidance: use dry_run=true to preview, keep_tracks_in_sync=true for transcript cuts, and 'old must be copied exactly from a fresh ws_read' tells the agent the prerequisite read step. It does not, however, address when to prefer this over sibling run_timeline_batch for timeline changes, nor when the confirm flag should be used.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.