Skip to main content
Glama

create_site

Create a new site on a free subdomain. It stays empty until you publish files with write_files or start_upload. Before creating one, check what it is for against what Hostlo does not host (in the server instructions and /llms.txt), and tell the person first if it is not allowed.

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": "create_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoDesired subdomain: 3-63 lowercase letters, digits and hyphens. Omit for a random name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, non-destructive write, so the bar is lower; the description still adds meaningful context beyond them — the result is a free subdomain, it starts empty, and content only appears after publishing. It also discloses a policy gate and a requirement to surface disallowed purposes to the user. Undisclosed behaviors remain, such as what happens on a duplicate name or how ownership of the new site is assigned.

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?

Three sentences, front-loaded with the core action, and each carries distinct information: what is created, when content appears, and the pre-flight policy check. The policy sentence is slightly convoluted with its parenthetical file references but still readable and non-redundant.

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?

For a one-parameter tool with no output schema, the description covers the action, the empty-until-published state, and the compliance check that gates creation. It could say more about what is returned on success (site identifier or URL) and failure modes like name collisions, but the essentials for correct invocation are present.

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 single 'name' parameter is already documented with length, character rules, and the omit-for-random behavior. The description adds no further meaning about the parameter — it only restates that the subdomain is free. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb and resource ('Create a new site') and narrows scope to a 'free subdomain,' so the agent knows exactly what is produced. It also positions the tool in the lifecycle by noting the site 'stays empty until you publish files with write_files or start_upload,' which implicitly separates it from those publishing siblings. It stops short of explicitly distinguishing creation from import_site, which is the nearest alternative.

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 a concrete precondition before invocation: check the intended purpose against what the host does not allow, with explicit pointers to the server instructions and /llms.txt, and instructs the agent to inform the person first if disallowed. That is real when-to-use guidance plus a follow-up path via write_files or start_upload. The gap is that it never says when import_site or rename_site would be the better choice instead of creating fresh.

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