Skip to main content
Glama
Sign In

AskEditor

by com.askeditor
OverviewDiscussionsAdmin

Watch the edit

watch_edit
Read-onlyIdempotent

[read] WATCH THE EDIT as it will export, as timestamp grids, overlays and captions included. After every visible change, before saying it is done. Footage alone is watch_clip; exact positions read_clip. Sheets [{asset_id, grid, fromMs, toMs, cells}]; continueFromMs; layout {errors, warnings, findings [{severity, rule, message, fix, atMs}]} in pixels; failed_graphics [{asset_id, title, error}] left out. Fix every error as its fix says. Related: watch_clip, read_clip, get_timeline. Full docs: load_skill with tools: [name].

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": {
      "project_id": "<project_id>"
    },
    "name": "watch_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
fpsNoFrames sampled a second. Default 1, fewer when a long stretch needs it.
toMsNoEnd of the stretch, ms. Default the end.
fromMsNoStart of the stretch, ms. Default the start.
guidesNotrue: draw 10% grid lines with 20/40/60/80 marks.
assetIdNoOne motion graphic alone.
timesMsNoExact moments instead of a range, ms.
project_idYesThe AskEditor project this acts on (from list_projects).
cellsPerSheetNoFrames per sheet: fewer = bigger cells. Default 12 (16 past 72 s).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds real context: the return payload is timestamp grids with overlays and captions, layout findings are in pixels with severity/rule/message/fix, and failed graphics are omitted from the result. It doesn't mention whether the call consumes render credits or what the sheets physically contain (images vs. text), which matters given the request_budget/wait_for_credits siblings.

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 the action and the sibling routing before any payload detail, and no sentence is decorative. The telegraphic phrasing ("After every visible change, before saying it is done.") is terse to the point of being slightly cryptic, but it avoids padding.

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 an 8-parameter, no-output-schema tool, the description compensates by sketching the return structure, partial-failure handling, and pagination, plus routing to the right sibling. Remaining gaps — cost/credit implications and what a "sheet" actually is as an artifact — are non-trivial but secondary to calling it correctly.

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% and every parameter — fps, fromMs/toMs, timesMs, cellsPerSheet, assetId, guides — already carries its own description, so the baseline of 3 applies. The description's field-like tokens (asset_id, grid, fromMs, toMs, cells, continueFromMs) describe the response shape rather than adding meaning to the inputs.

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?

"[read] WATCH THE EDIT as it will export" names a specific verb and resource, and the definition actively draws boundaries against siblings ("Footage alone is watch_clip; exact positions read_clip"). The phrasing is slightly oblique — an agent must infer that this renders a preview of the composed edit rather than the source footage — but the differentiation is explicit enough to pick the right tool.

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

Usage Guidelines5/5

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

Gives an explicit trigger ("After every visible change, before saying it is done") and names the two alternatives with the conditions that select them (watch_clip for footage alone, read_clip for exact positions). This is the when/when-not/alternative pattern done well.

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

All AskEditor toolsInspect
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