Skip to main content
Glama

Niche of One Network

Start a site build

start_site_build

A guided brief for a hand-built website from Niche of One: asks for what is missing one step at a time, then shows the brief and the published prices. Sends it only on a second call with confirm true. Contact details are not taken here. Best shown as a step-by-step artifact.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_site_build"
  }
}

Input Schema

NameRequiredDescriptionDefault
nicheNoWhat you do and who the site is for.
notesNo
pagesNo
budgetNo
confirmNoLeave out to preview; true to send.
contactNoaccount_email (signed-in members) or form.
examplesNoSites or features you like.
timelineNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations only declare the generic safe-write profile (readOnly=false, destructive=false, not idempotent, closed world). The description adds genuinely non-obvious behavior: a preview-then-confirm two-phase flow, incremental single-question prompting, and the fact that contact details are not collected here. It stops short of saying what happens to the brief after confirm is sent.

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?

Four short sentences, front-loaded with what the tool is, followed by the confirm gate and the display suggestion. Nothing is redundant, though the trailing rendering hint ('Best shown as a step-by-step artifact') is slightly outside the core behavior statement.

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 an 8-parameter creation/submission tool with no output schema, the essential flow (collect → preview → confirm) is covered. However, the description never says what the agent should expect after a confirmed send, and the interaction with the existing-brief siblings is unstated, leaving a real gap for a multi-turn 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?

With 8 parameters at 50% schema coverage, the description only reinforces two of them meaningfully: confirm=true means send versus preview, and it clarifies that contact lives elsewhere. The remaining fields (niche, notes, pages, budget, examples, timeline) are left to their self-explanatory enums and brief schema notes, so it neither compensates for nor worsens the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete verb and resource: it gathers a guided brief for a hand-built website, previews it with published prices, and only sends on a second call. That is specific enough to separate it from siblings like my_brief or buy, though the opening phrase 'A guided brief' frames the action more as an artifact than as a submission step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

It implies the correct usage pattern ('a second call with confirm true', 'asks for what is missing one step at a time') and rules out taking contact details here. There is no explicit statement of when to prefer this over viewing an existing brief (my_brief) or purchasing (buy), so the agent must infer the routing.

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.

Resources