Skip to main content
Glama

Hand over to WhatsApp

get_whatsapp_handoff
Read-only

Generate a pre-filled WhatsApp deep link to hand the customer off to the right contact. Garden Route locations (Knysna, Plett, George, Sedgefield, etc.) route to Duncan Kane on WhatsApp (+27795235407) for a free in-home consultation. Awnings, shutters, shadeports and Ziptrak, named in product_context, route to Duncan Kane from anywhere in South Africa. Everything else routes to the shop WhatsApp (+27760228410), WhatsApp only, no voice calls. Use when the customer prefers human assistance or when self-serve checkout isn't appropriate.

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": "get_whatsapp_handoff"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageNoOptional additional message to prefill
locationNoCity/suburb. Garden Route locations route to Duncan.
customer_nameNo
product_contextNoe.g. 'roller blockout for bedroom'. Awnings, shutters, shadeports or Ziptrak here route to Duncan.

Output Schema

NameRequiredDescriptionDefault
reasonYes
recipientYes
whatsapp_urlYes
recipient_phoneYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / location / description
      Previous value: -"City/suburb. Drives Duncan vs shop routing."New value: +"City/suburb. Garden Route locations route to Duncan."
    • changedInput schema / properties / product_context / description
      Previous value: -"e.g. 'roller blockout for bedroom'"New value: +"e.g. 'roller blockout for bedroom'. Awnings, shutters, shadeports or Ziptrak here route to Duncan."
  2. Changed1 schema field changed
    • removedInput schema / properties / customer_name / description
      Removed value: -"Customer's name, used in the prefilled WhatsApp message."
  3. Changed1 schema field changed
    • addedInput schema / properties / customer_name / description
      Added value: +"Customer's name, used in the prefilled WhatsApp message."
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "properties": {
      +    "reason": {
      +      "type": "string"
      +    },
      +    "recipient": {
      +      "type": "string"
      +    },
      +    "recipient_phone": {
      +      "type": "string"
      +    },
      +    "whatsapp_url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "whatsapp_url",
      +    "recipient",
      +    "recipient_phone",
      +    "reason"
      +  ],
      +  "type": "object"
      +}
  5. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds real behavior: it builds a link rather than sending a message, routing differs by geography vs. product, and the channel is 'WhatsApp only, no voice calls'. It stops short of saying what the tool returns or whether it opens a session, so not a 5.

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?

Front-loaded with the core action, then the routing table, then the trigger condition — a sensible order. The phone numbers and repeated destination names are verbose but functional, and a few clauses restate what the schema already says.

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?

An output schema exists, so return values needn't be described. The description covers the fallback case ('everything else routes to the shop WhatsApp'), the channel constraint, and both routing dimensions, leaving no decision an agent must make before calling it unaddressed.

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 75%, and the description supplies the missing meaning: it explains that location and product_context are routing inputs, not just free text, and spells out which values (Knysna/Plett/George/Sedgefield; awnings/shutters/shadeports/Ziptrak) change the destination. Only customer_name is left without added semantics.

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 artifact ('Generate a pre-filled WhatsApp deep link') plus the intent ('hand the customer off to the right contact'). The routing rules make it unmistakably the human-handoff tool rather than any catalog/cart/checkout sibling.

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?

Gives an explicit trigger ('when the customer prefers human assistance or when self-serve checkout isn't appropriate'), which implicitly excludes self-serve-appropriate cases. It does not name a specific alternative tool or a hard 'do not use when' rule, keeping it short of a 5.

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.