Skip to main content
Glama

Edit a draft

autoshort_update_draft
Destructive

Edit a video draft before rendering: update scene narration, visuals, or timing, and insert, reorder, or remove scenes to finalize the script.

Instructions

Change a draft before render. Free. Every scene number refers to the draft as it is now (1-based); operations apply in the order edits, reorder, remove, insert. edits: change a scene's narration (verbatim), visual (null clears it → auto image) or seconds. insert: add scenes after scene N (0 = at the start). remove: scene numbers to drop. reorder: every current scene number in the new order. Returns the updated draft — show it to the user again.

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": {
      "draftId": "<draftId>"
    },
    "name": "autoshort_update_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
editsNo
titleNoHeadline shown over the first 1.5s and used as the video title. Defaults to the first sentence.
insertNo
removeNo
draftIdYes
reorderNo
artStyleNoVisual style; see autoshort_list_niches. Default AUTOSHORTS (cinematic photography).
languageNoBCP-47 narration language ("en", "vi", …). Omit to detect it from the narration.
aspectRatioNo
targetDurationNoRequested length in seconds. Kept as requested — if the verbatim narration cannot fit it, warnings[] says so with a word count that would.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds genuinely new behavior: the tool is free, scene numbers are 1-based against the *current* draft state, operations are applied in a fixed order (edits, reorder, remove, insert), and null visual clears to an auto image. It does not mention what errors or warnings[] look like on a partial failure, which would have been the final piece.

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 purpose, then a compact per-operation breakdown; every clause carries information. The single dense paragraph runs long and the operation-order clause sits before the operations are defined, which costs a little readability.

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 a 10-parameter destructive mutation with only 40% schema coverage and no output schema, the description covers the tricky array parameters well but leaves the draft-level settings (artStyle, language, aspectRatio, targetDuration) and draftId undescribed. It also mentions the returned draft but not warnings[], which the schema references in two places.

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 schema coverage at 40%, the description carries real weight: it defines edits (verbatim narration, null visual clears it, seconds), insert (after=N with 0 meaning start), remove, and reorder (must list every current scene number). These are non-obvious semantics the schema does not state, though title, artStyle, language, aspectRatio and targetDuration are left entirely to their schema text.

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 and resource ("Change a draft before render") and explicitly scopes it to the pre-render stage, which distinguishes it from autoshort_render_draft and autoshort_get_draft without naming them. The rest of the description reinforces this by describing draft-mutation operations only.

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?

"before render" and "Returns the updated draft — show it to the user again" give a clear working context, and the operation-ordering sentence tells the agent how the call behaves in practice. It stops short of naming an alternative (e.g. get_draft to read, render_draft to publish) or stating exclusions, so it is clear context rather than full when/when-not guidance.

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