Skip to main content
Glama

Change a booth draft's settings

update_booth_draft
DestructiveIdempotent

Change a booth draft without a redraw: its title, link name, welcome button text, colours, capture mode, language, which frames and filters it carries, its AI effect, and the page settings the dashboard editor offers (photo count, countdown, timeouts, GIF/recording, retake, checkout, payment, result). Use it after check_generation shows the draft and the operator asks for one of these; what it sets is applied when create_booth runs. It cannot change the welcome headline or subtext of an AI-designed welcome (those are painted into the image — use refine_booth with what='welcome' and headline), and prices or packages are set in the dashboard. Answers at once with the updated draft, applied (what landed) and rejected (what did not, and why) — relay a rejection as a sentence, never as success. It never touches a booth that already exists.

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": "update_booth_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoThe proposed link name (dreambooth.app/<slug>): lowercase letters, digits, single hyphens. Checked for availability; a taken one is reported, not stored.
titleNoThe booth's name (used as the title at create time).
draftIdYesThe draft to change, from check_generation or get_booth_draft.
paletteNoTheme colours as #RRGGBB: primaryColor, secondaryColor, backgroundColor. Only the ones given change.
subtextNoWelcome subtext; same rule as headline.
frameIdsNoFrames the booth should carry (replaces the draft's list): e.g. one saved with save_frame, or catalogue ids. create_booth adds starter frames anyway.
headlineNoWelcome headline. Only drafts whose welcome is laid out as text accept it; on an AI-designed welcome it is painted into the image: use refine_booth with what='welcome' and headline instead.
languageNoLanguage code of the booth's own text: 'id', 'en', 'es'.
settingsNoPage settings, as the dashboard editor has them, keyed by page: welcome{startWithPayment}, capture{captureCount 1-10, captureCountdown 1-15, prepTimeout, captureTimeout, selfPhotoDuration, gifEnabled, gifSpeed, recordingEnabled, recordingSpeed}, retake{enabled, retakeTimeout, maxRetakeCount, maxRetakeSession}, select{enabled, selectionTimeout}, frame{displayFrameTitle}, filter{enabled, useLivePreview, applyAfterCapture}, checkout{enabled, checkoutTimeout, promoEnabled}, payment{enabled, paymentTimeout}, result{resultTimeout, askUserConsent, emailEnabled, reprintEnabled, reprintTimeout}. Prices and packages are set in the dashboard, not here.
filterIdsNoFilters the booth should carry (replaces the draft's list): e.g. one made with create_filter. The default 'Normal' is added anyway.
buttonTextNoThe welcome screen's button label, e.g. 'Mulai' or 'Start'.
captureModeNo'standard' = classic strip, 'frame-based' = frame mode.
aiEffectTitleNoThe title of a public AI effect to add, exactly as the operator named it; an empty string removes the one chosen before.

Output Schema

NameRequiredDescriptionDefault
kindYes
noteNo
whatYes
draftNo
errorNo
jobIdYes
stateYes
appliedNo
draftIdYes
rejectedNo
slugAvailableNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / headline / description
      Previous value: -"Welcome headline. Only drafts whose welcome is laid out as text accept it; on an AI-designed welcome it is painted into the image and the reply says to use refine_booth."New value: +"Welcome headline. Only drafts whose welcome is laid out as text accept it; on an AI-designed welcome it is painted into the image: use refine_booth with what='welcome' and headline instead."
  2. Added

TDQS

A4.9/5.0
Behavior5/5

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

Goes well past the annotations by explaining the deferred-application model (changes land when create_booth runs), the partial-update semantics (only supplied palette colours change; frame/filter lists are replaced), and the applied/rejected response contract with an instruction to relay rejections as sentences rather than success. None of that is inferable from destructiveHint/idempotentHint alone.

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 usage, then limitations and response shape — a sensible order with no filler sentences. It is dense to the point of being a single sprawling paragraph, and the long comma-separated field catalogue in the first sentence costs more reading effort than a structured breakdown would.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter nested mutation tool this covers what an agent needs: when to call it, what it silently defers to create_booth, what it refuses to touch, and how failures surface. With an output schema present, it correctly stops short of describing the return payload in detail while still flagging the applied/rejected split that affects how results should be reported.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description still adds operational meaning the schema lacks: slug availability is checked and a taken one is reported rather than stored, frameIds/filterIds replace rather than append, a default 'Normal' filter is added regardless, and an empty aiEffectTitle removes a prior choice. Those are behavioural distinctions, not restatements.

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+resource ("Change a booth draft") and then enumerates exactly which fields it governs: title, link name, button text, colours, capture mode, language, frames, filters, AI effect, page settings. It also draws a hard boundary that separates it from create_booth, refine_booth and the dashboard editor, so an agent can place it among siblings 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 Guidelines5/5

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

Gives an explicit trigger ("after check_generation shows the draft and the operator asks for one of these") and an explicit routing rule for the case it cannot serve ("use refine_booth with what='welcome' and headline"). It also names a second exclusion — prices/packages live in the dashboard — and states it never touches an existing booth.

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.