Skip to main content
Glama
Sign In

AI Site Builder: website preview

by com.adcreator-ai.sitebuilder
OverviewDiscussionsAdmin

Build a website preview for a small business

build_site_preview

Builds a real, complete website preview for a small business from a one-sentence description (optionally its name and city), using AI Site Builder (sitebuilder.adcreator-ai.com). Returns a link to the live preview and a one-tap link to publish it as the person's free site (set a password, then Go Live). No signup or email needed to see the preview; it expires after 72 hours unless claimed. Limited to 3 previews per hour per network. Use it when someone wants to see what a website for their business could look like.

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": {
      "description": "<description>"
    },
    "name": "build_site_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoOptional city or area, e.g. "Tacoma, WA".
descriptionYesOne sentence describing the business, e.g. "Family-run wood-fired pizzeria, takeout and dine-in, since 2019."
business_nameNoOptional business name. If omitted the preview shows an editable "Your Business Name" placeholder.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / business_name / description
      Previous value: -"Optional business name. If omitted it is taken from the first phrase of the description."New value: +"Optional business name. If omitted the preview shows an editable \"Your Business Name\" placeholder."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, it discloses that the tool hits an external service, needs no signup or email, returns both a live-preview link and a one-tap publish link, and that the preview expires after 72 hours unless claimed. These are exactly the operational facts an agent needs, and none of them contradict the openWorld/readOnly 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?

A single tight paragraph that is front-loaded with purpose, then consequence (returned links), then operating constraints (no signup, 72-hour expiry, rate limit), and finally the usage trigger. Every sentence carries distinct information with 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?

There is no output schema, and the description compensates by explaining what is returned (a preview link plus a publish link) and what the publish flow involves. Combined with the expiry and rate-limit disclosures, nothing material is missing for a three-parameter, external-service tool.

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% and the schema already documents all three fields, including optionality, length bounds and examples. The description only restates that name and city are optional and that the core input is a single sentence, adding little beyond the structured schema, so baseline 3 applies.

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?

The description opens with a specific verb and resource: 'Builds a real, complete website preview for a small business from a one-sentence description,' and names the backing service (AI Site Builder). An agent knows exactly what the tool produces and what input it needs, with no sibling tools to confuse it.

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?

It gives an explicit usage trigger: 'Use it when someone wants to see what a website for their business could look like,' and bounds calls with a stated rate limit of 3 previews per hour per network. It lacks a when-not-to-use exclusion, but with no sibling tools there is no alternative to route to, so the gap is minor.

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

All AI Site Builder: website preview 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