Skip to main content
Glama

Update project style

update_project_style
DestructiveIdempotent

Change a project's caption and hook styling, fades, and intro/outro transitions across all clips, clearing per-clip overrides by default and re-rendering finished clips unless disabled.

Instructions

Change the caption/hook look and fades for the whole project (colors, size, position, words per line, fadeIn/fadeOut, intro/outro bumperTransition). Clears per-clip style overrides unless keepOverrides, and re-renders every finished clip unless rerender is false. Returns { changed, needsRerender, rerendered, skipped, hint }; rerendered is how many clips were queued, skipped how many were still preparing or rendering (they need rerender_clips once done). For one clip use update_clip { style }.

Input Schema

NameRequiredDescriptionDefault
idYesProject id (from list_projects, search_clips or create_project)
styleYesThe style fields to change; fields left out keep their value
rerenderNoRe-render finished clips now (default true); false saves the style and the next render shows it
keepOverridesNoKeep clips' own style overrides instead of clearing them (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.33.0
    • addedInput schema / properties / style / properties / bumperTransition
      Added value: +{
      +  "description": "How the intro/outro joins the clip: cut (default), dip (fade through black, no change in length) or crossfade (the two overlap, so the video is shorter by the transition)",
      +  "enum": [
      +    "cut",
      +    "dip",
      +    "crossfade"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / style / properties / bumperTransitionSec
      Added value: +{
      +  "description": "Length of the intro/outro transition, seconds (0.2-2, default 0.5); ignored for cut",
      +  "maximum": 2,
      +  "minimum": 0.2,
      +  "type": "number"
      +}
    • addedInput schema / properties / style / properties / fadeIn
      Added value: +{
      +  "description": "Fade in from black (picture and sound) at the start of the video, seconds (0-2, default 0 = off)",
      +  "maximum": 2,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / style / properties / fadeOut
      Added value: +{
      +  "description": "Fade out to black (picture and sound) at the end of the video, seconds (0-2, default 0 = off)",
      +  "maximum": 2,
      +  "minimum": 0,
      +  "type": "number"
      +}
  2. Changed1 schema field changedv0.28.1
    • addedInput schema / properties / style / properties / captionSeam
      Added value: +{
      +  "description": "In split and stack sections, put captions on the line between the two panes instead of at captionY (default true)",
      +  "type": "boolean"
      +}
  3. Addedv0.26.3

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description goes further by naming exactly what is destroyed ('clears per-clip style overrides unless keepOverrides') and what collateral work is triggered ('re-renders every finished clip unless rerender is false'). That is the specific consequence detail an agent needs before calling a destructive mutation, and it is consistent with the annotations.

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?

Four tight sentences: purpose first, then destructive side effects, then return shape, then sibling routing. No filler, and the highest-risk information (override clearing, re-render cost) is placed before the return-value detail.

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?

There is no output schema, so the description's explanation of the return object ({ changed, needsRerender, rerendered, skipped, hint }) and what rerendered/skipped count is genuinely necessary and supplied. For a mutation with a 17-field nested style object it covers behavior and results well; only minor gaps remain, such as whether the re-render is synchronous or how long queueing takes.

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%, including nested style fields, so the baseline is 3. The description adds some framing by grouping the style keys and flagging the keepOverrides/rerender consequences, plus explaining that skipped clips need rerender_clips, but individual parameter meaning is almost entirely carried by the schema.

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 with explicit scope ('for the whole project') and enumerates the style dimensions affected (caption look, colors, size, position, words per line, fades, bumper transitions). It also explicitly separates itself from update_clip, so an agent can distinguish project-wide styling from per-clip styling without opening either schema.

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 alternative ('For one clip use update_clip { style }') and, in the return-value sentence, routes agents to rerender_clips for clips that were still preparing ('they need rerender_clips once done'). It also implicitly defines when to disable behavior via keepOverrides and rerender=false, so both selection and invocation conditions are covered.

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