Skip to main content
Glama

create_simple_conversation

Create a simple bot auto-reply rule. When a customer sends a message matching the trigger keyword, the bot replies with the specified text. With "ask_contact" the reply asks for the customer's phone number or e-mail with a one-tap Messenger button (text only on other channels); "confirmation" is then sent once after the customer taps it.

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": {
      "hear": "<hear>",
      "text": "<text>"
    },
    "name": "create_simple_conversation"
  }
}

Input Schema

NameRequiredDescriptionDefault
hearYesTrigger keyword or phrase that activates this reply
textYesReply message text to send when triggered. With "ask_contact" it is the question shown above the button and may be "" (= a standard question in the workspace language).
agent_idNoOptional moderator ID to auto-assign to the contact when triggered
channelsNoOptional. Channels this rule replies on, e.g. ["instagram", "messenger"]. Omit or [] = every channel (default). "whatsapp" covers both official and unofficial WhatsApp numbers. On other channels the message falls through to the other rules, the default reply or the AI.
label_idNoOptional label ID to auto-assign to the contact when triggered
ask_contactNoOptional. Make the rule ask the customer for their phone number ("phone") or e-mail ("email") with one tap. On Facebook Messenger the reply text goes out with a quick-reply button pre-filled from the customer's Facebook profile (hidden by Meta when the profile has no such value); the tapped value is saved on the contact (e-mail field when empty, otherwise an internal note; phone always as an internal note). Instagram has no equivalent (Meta disabled it), so Instagram, WhatsApp and other channels receive the text only and the customer types the answer; a typed phone number / e-mail (within 24 hours of the ask) is saved the same way. "text" is optional with this argument: empty = a standard question. The rule must reply on Messenger (channels [] or including "messenger").
confirmationNoOptional, with an "ask_contact" rule only. Confirmation message sent ONCE on the same channel and in the same conversation right after the customer taps the Messenger button and shares the phone number / e-mail, or — on any channel — types one in their next messages within 24 hours of the ask, e.g. "Thanks, we'll contact you by WhatsApp". While it is set, neither keyword rules nor the AI answer that message. Max 2000 characters.
match_messageNoIf true, requires exact match. If false, partial/fuzzy match (default: false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare this is a non-readOnly, openWorld, non-idempotent write operation. The description adds meaningful behavior beyond annotations: channel fallthrough, one-tap ask_contact limitations on Instagram/WhatsApp, the one-time confirmation, and suppression of other keyword rules and AI while confirmation is set. It does not discuss permissions, rate limits, or returned data, so it is rich but not exhaustive.

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 the core create action and trigger/reply behavior. It is appropriately sized overall, though the ask_contact sentence is long and dense with channel-specific caveats.

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?

Given the rich schema coverage and no output schema, the description is sufficiently complete for an agent to call the tool correctly. It covers the main behavioral mechanics and ask_contact/confirmation nuances, with the main gap being explicit sibling selection guidance.

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%, so all parameters are already documented in the input schema. The description reinforces ask_contact and confirmation semantics, but adds little beyond what the schema already provides, making 3 the correct baseline.

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 states a specific verb and resource: "Create a simple bot auto-reply rule." It explains the trigger/reply model clearly, so an agent can understand what the tool produces. It does not explicitly distinguish this from the sibling create_interactive_conversation tool, which keeps it from a 5.

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?

Usage is implied through the explanation of trigger keywords and the ask_contact/confirmation flow, including the Messenger channel requirement. However, the description gives no explicit guidance on when to choose this simple rule versus create_interactive_conversation or other bot-creation tools, and no when-not conditions.

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