Skip to main content
Glama

send

Delivers WhatsApp text messages from your own account, quotes replies, and forwards existing messages or media to a phone number or chat JID.

Instructions

Send a WhatsApp text message from the user's own account, or forward one. to is a phone number in international format or a chat JID (v_chats.jid — the only way to address a group). Optional reply_to is the v_messages.stanza_id of a message in that chat to quote. To forward instead, give forward (a v_messages.stanza_id from any chat: text, link, image, video, GIF, sticker, voice note or document) and no text. Irreversible and seen by real people: send only what the user explicitly asked for, to the chat they named. Needs whatskept live running.

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": {
      "to": "<to>"
    },
    "name": "send"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesphone number in international format (+971501234567) or a chat JID from v_chats.jid
textNothe message text; omit when forwarding
forwardNooptional: v_messages.stanza_id of a message (any chat) to forward to 'to' — instead of text
reply_toNooptional: v_messages.stanza_id of a message in the same chat to reply to (quote)

Output Schema

NameRequiredDescriptionDefault
idYesthe message's stanza ID (ZSTANZAID in the database)
tsYessend time, UTC ISO
chatYesthe chat JID the message went to
warningNoset when the message was sent but not recorded in the database; do not resend

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.24

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations at all, the description carries the full burden and does so well: it discloses irreversibility ('Irreversible and seen by real people'), the runtime precondition (live bridge running), the group-addressing constraint (JID is the only way to reach a group), and the range of forwardable media types. These are exactly the behavioral facts an agent cannot get from the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The primary action and its scope come first, then the forward branch, then the safety warning. Every clause earns its place: nothing is repeated from the schema verbatim and no sentence is filler.

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 a four-parameter mutating tool with no annotations, the definition covers purpose, modes, targeting, preconditions, and irreversibility, and the output schema handles return values. What remains unstated is failure behavior (invalid JID, bridge offline) and any rate limits, which would matter for a send operation.

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 100%, so baseline is 3, but the description adds real semantics: `to` accepts a phone number or a v_chats.jid, `forward` must come with no `text`, and `reply_to` must be a stanza_id from the same chat while `forward` may come from any chat. That same-chat vs any-chat distinction is a genuine constraint not obvious from the schema alone.

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 concrete verb and resource ('Send a WhatsApp text message from the user's own account, or forward one') and covers both operating modes. An agent knows exactly what will happen in the world after reading the first sentence.

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?

The text-vs-forward choice is explicit: 'To forward instead, give `forward` ... and no `text`.' It also constrains targeting ('to the chat they named') and states the precondition 'Needs `whatskept live` running.' It does not reference sibling tools, but none of the listed siblings (get_schema, query, search) appear to be send alternatives, so there is little to differentiate.

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

Deploy Server

Other Tools