Skip to main content
Glama

Start a direct chat

start_chat

Open a direct chat by user ID, phone number, username, or email and return its chat ID for sending messages or files. Reuses an existing chat when available.

Instructions

Open a direct chat with someone, even if you have never messaged them on this account, and return its chatID so you can then send messages or files. Reuses the existing chat when there is one. Identify the person with userID (from search_contacts), phoneNumber, username or email. Some networks need a first message to create the chat: pass it in messageText (it is sent immediately; confirm with the user first).

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": {
      "accountID": "<accountID>"
    },
    "name": "start_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailNoEmail address
userIDNoContact ID from search_contacts
fullNameNoDisplay name, only used to rank candidates
usernameNoUsername / handle
accountIDYesAccount to start the chat on, e.g. whatsapp.33612345678
messageTextNoFirst message, only if the network requires one to create the chat
phoneNumberNoPhone number, E.164 preferred (+33612345678)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag openWorldHint and non-read-only, but the description adds the material behavior the annotations cannot convey: messageText is sent immediately to a real person and should be confirmed with the user first, and only some networks need it. Reuse of an existing chat is also disclosed. Missing: what happens on ambiguous or unresolved identities, and failure modes for unknown accounts.

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?

One front-loaded paragraph that leads with the action and payoff, then identity options, then the network caveat. Dense and largely waste-free, though the final clause bundles the message-immediacy warning into a long sentence rather than surfacing it more prominently.

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?

With no output schema, the description correctly supplies the return value (chatID) and its intended downstream use. For a 7-parameter external-network tool, it covers the main decision points; the residual gap is guidance on ambiguous candidates and error behavior, which matters given that fullName only ranks candidates.

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 coverage is 100%, so the baseline is 3. The description does add value by grouping the four identity options (userID, phoneNumber, username, email) as interchangeable identification routes and by clarifying that messageText is conditional on the network. It does not mention accountID or fullName at all, and does not say whether the identity parameters are mutually exclusive or how ties are broken when several are supplied.

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 (open a direct chat) plus the concrete payoff (returns chatID to then send messages or files). It also disambiguates from search_contacts, which is named as the source of userID, and from send_file/send-message siblings by framing this as the prerequisite step.

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?

Clear context for use: reach someone never messaged on this account, and the note that an existing chat is reused tells the agent this is safe to call instead of first checking for a chat. It names search_contacts as the way to obtain userID. It does not state when to prefer an existing-chat lookup or what to do if the contact cannot be resolved.

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