WebinarStack

Update Widget Style Draft

webinarstack.webinars.widget_style_update

Idempotent

Update a tenant-owned webinar's widget style draft with a JSON merge patch; send only the keys you change. The live widget does not change until you call webinarstack.webinars.widget_style_publish. This changes the widget's style object only. It is not page-builder authoring: it cannot add, remove or edit blocks or form fields. Writable in this version: host.modalWidth (integer 320-1200) and host.triggerColor, plus the form options: surface (bg, maxWidth, borderWidth, borderColor, radius, shadow, padding), typography (headingFont, bodyFont, headingScale, headingWeight, align), header (logoPlacement, kickerStyle, trustStyle), fields (labelStyle, fieldStyle, fieldBorder, fieldRadius, fieldSize, fieldBg), button (buttonStyle, buttonShape, buttonWidth, buttonSize, buttonIcon, buttonColor), session picker (sessionStyle), countdown (countdownStyle) and layout (blockSpacing, blockTitle). Colour values accept hex (#rgb, #rrggbb), rgb() or rgba(), and some colours also take a keyword (bg: transparent, borderColor: auto, fieldBg: auto or translucent). An absent headingFont or bodyFont follows the webinar theme font. null removes an option so it falls back to its default. Options for the modal chrome and the trigger button (Phase 231) and for the surface kind, colour scheme, text tone, layout and panel (Phase 233) return 'not yet available'. Last write wins. Responses include updatedAt. An editor tab that is open on this widget can autosave over a draft written through the API.

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": {
      "webinarId": "<webinarId>",
      "style": "<style>"
    },
    "name": "webinarstack.webinars.widget_style_update"
  }
}

Input Schema

Name	Required	Description	Default
`style`	Yes	RFC 7396 merge patch for the widget style object. Send only the keys you change; null removes an option.
`webinarId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only cover the safety profile (readOnly=false, idempotent=true, destructive=false, openWorld=false); the description goes well past that with last-write-wins conflict behavior, autosave collision risk from the editor UI, null-as-removal semantics that restore defaults, inherited fallbacks for headings/fonts, unsupported Phase 231/233 options returning 'not yet available', and updatedAt in the response. These are exactly the traits an agent cannot infer from 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and patch semantics, then constraints, then the key inventory. It is a dense single paragraph and the long enumeration of writable keys largely repeats schema enum lists, which costs some readability, but each sentence carries substantive content and there is no filler.

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?

With no output schema, the description still reports that responses include updatedAt, and it covers mutation risk, concurrency, default restoration, and unsupported options — everything needed to call a nested merge-patch tool correctly. Nothing material for correct invocation is left unstated.

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?

The schema already documents nearly every style property with enums and ranges, so the description's per-key listings are largely redundant. It still adds meaning the schema does not: the grouped phase boundaries that determine which keys are rejected as 'not yet available', the accepted colour syntaxes and keyword exceptions, and the headingFont → bodyFont → theme font inheritance chain.

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 (update), a specific resource (a tenant-owned webinar's widget style draft), and the exact write semantics (JSON merge patch, send only changed keys). It also explicitly bounds scope away from page-builder authoring and separates itself from widget_style_publish, so an agent can distinguish it from siblings without opening any 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?

Explicit routing: the live widget does not change until widget_style_publish is called, which names the follow-on tool and the condition. It also states a clear exclusion ('not page-builder authoring: cannot add, remove or edit blocks or form fields') and warns that an open editor tab can autosave over an API-written draft, which is genuine when-to-use guidance.

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

All WebinarStack tools Inspect

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

Need Help?