Latchbell

Message the customer

message_customer

Owners only (needs sign-in): Answer a customer's or another business's question (inquiry_id, from customer.message, updates or inquiries), or message a customer about a confirmed booking (booking_id). Latchbell relays it, and neither side sees the other's contact details until they book. Answer from what Latchbell knows and what the owner told you; ask the owner about anything else, and never negotiate prices. A question that came by text (via: text message) is answered by text: short and plain, no markdown. sent: false means it was already answered: don't retry. follow_up: true only when the owner wants another message. Up to 500 characters.

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": "message_customer"
  }
}

Input Schema

Name	Required	Description
`message`	Yes
`follow_up`	No	Send even though the customer's latest message was already answered; only when the owner asked for another message
`booking_id`	No
`inquiry_id`	No	Instead of booking_id: answer in a conversation

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond readOnlyHint=false and openWorldHint=true, it discloses the relay behavior (neither side sees contact details until they book), the 500-character cap, the meaning of a sent: false result, and the no-retry rule. These are non-obvious operational traits an agent could not get 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?

Dense but front-loaded: the two modes come first, then constraints and failure semantics. Every sentence carries operational content, though the follow_up clause duplicates the schema description verbatim and the middle sentence is a long compound that could be split.

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?

For a 4-parameter mutation tool with no output schema, the description covers the caller's prerequisites, the two addressing modes, formatting rules, and even the sent: false return condition, so an agent has everything needed to call it and interpret the result.

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?

Schema coverage is 50%: booking_id and message have no schema descriptions. The description compensates by explaining that inquiry_id is used 'instead of booking_id' to answer in a conversation, that booking_id targets a confirmed booking, and by tying message to the 500-character limit and the plain-text rule for text-message questions. Only follow_up largely restates the schema.

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 gives a specific verb+resource pair and splits it into two clear modes: answering an inquiry (inquiry_id) versus messaging about a confirmed booking (booking_id). It is slightly weaker on sibling differentiation, since it never contrasts itself with adjacent tools such as contact_business or ask_business, leaving the agent to infer the boundary from the parameter shapes alone.

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?

It states when to use each mode explicitly ('answer in a conversation' vs 'about a confirmed booking'), adds the precondition 'Owners only (needs sign-in)', and gives concrete exclusions: ask the owner about anything else, never negotiate prices, do not retry when sent: false, follow_up only when the owner asked for another message. That is when/when-not/alternative coverage in one place.

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?