Latchbell

Message the website designer

site_designer_chat

Owners only (needs sign-in): Message Latchbell’s website designer, as the owner does in the dashboard. It works in the background, often for minutes, and this answers at once: read my_website about every 30 seconds until working is null and queued is 0. The last line of designer_chat says how it went: a designer line is its reply, a latchbell line means the turn didn’t finish. A message sent while it’s busy waits its turn. Use it sparingly, at critical steps (the first structure, a failed check, a redesign): it costs AI credits. For everyday changes prefer upload_site_pages.

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": {
      "message": "<message>"
    },
    "name": "site_designer_chat"
  }
}

Input Schema

Name	Required	Description	Default
`message`	Yes
`photo_ids`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing owner-only auth, background work that 'often for minutes', immediate return, polling my_website about every 30 seconds until working is null and queued is 0, queueing behavior when busy, credit cost, and how to interpret designer_chat versus latchbell lines. These are concrete behavioral traits an agent needs for correct invocation and follow-up.

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?

The description is front-loaded with auth and purpose, then gives operational details that earn their place. It is dense but mostly purposeful; minor phrasing like 'as the owner does in the dashboard' adds little.

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 an async, credit-consuming tool with no output schema, it covers the important workflow: immediate return, polling instructions, result interpretation, queueing, and cheaper alternatives. The main gap is the undocumented photo_ids parameter.

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

Parameters2/5

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

Schema description coverage is 0%, and the description never explains the two parameters. It implies a message is sent, but does not define message constraints, photo_ids, or when to attach photos, so it fails to compensate for the undocumented schema.

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 and resource: 'Message Latchbell’s website designer', with owner-only scope and a direct contrast to upload_site_pages for everyday changes. An agent can distinguish this from sibling tools 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 explicit when-to-use guidance: 'Use it sparingly, at critical steps (the first structure, a failed check, a redesign)' and says to prefer upload_site_pages for everyday changes. It also names the prerequisite: owners only and sign-in required.

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

All Latchbell 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?