Skip to main content
Glama
kiriminow
by kiriminow

send_message

Send a WhatsApp text or media message to a single recipient through a QR-scanned device, enabling direct customer replies.

Instructions

Send a WhatsApp text or media message to one recipient through a QR-scan device. This is the normal way to reply to a customer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageNoMessage text. Becomes the caption when media_url is set. Required unless media_url is given.
receiverYesPhone number in international format without + (e.g. 6281234567890), or a group JID
device_idNoDevice ID (e.g. D-XXXXX). Optional if the KIRIMI_DEVICE_ID environment variable is set.
media_urlNoPublic URL of an image, video, audio or document to attach. Max 50 MB. Required unless message is given.
quoted_message_idNoMessage ID to quote in the reply

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.1.0
    • addedInput schema / properties / device_id
      Added value: +{
      +  "description": "Device ID (e.g. D-XXXXX). Optional if the KIRIMI_DEVICE_ID environment variable is set.",
      +  "type": "string"
      +}
    • changedInput schema / properties / media_url / description
      Previous value: -"Optional public URL of image/video/document to attach"New value: +"Public URL of an image, video, audio or document to attach. Max 50 MB. Required unless message is given."
    • changedInput schema / properties / message / description
      Previous value: -"Text message to send"New value: +"Message text. Becomes the caption when media_url is set. Required unless media_url is given."
    • changedInput schema / properties / quoted_message_id / description
      Previous value: -"Optional message ID to quote/reply to"New value: +"Message ID to quote in the reply"
    • changedInput schema / properties / receiver / description
      Previous value: -"Recipient phone number (e.g. 628123456789) or group JID"New value: +"Phone number in international format without + (e.g. 6281234567890), or a group JID"
  2. First observedv1.0.0

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'through a QR-scan device,' implying device connectivity requirements, but it does not disclose rate limits, delivery semantics, potential errors, or whether the call blocks or is asynchronous. For a mutating send operation, this is a significant gap.

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?

Two sentences with zero filler. The core action and primary use case are front-loaded. The second sentence adds the 'normal way' positioning. It is efficient and readable, though slightly thin on detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description does not explain the response format (e.g., whether it returns a message ID or delivery status), error conditions, or limitations beyond the media size cap. It also omits guidance on how to construct a quoted message or handle missing device IDs. For a send tool with no annotations, this is incomplete.

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 five parameters are fully documented in the schema. The description adds no additional meaning beyond what the schema already provides—it doesn't clarify the mutual exclusivity of message and media_url, nor does it explain JID or device_id nuances beyond the schema. Baseline 3 is appropriate.

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?

The description states a clear verb-resource pair: 'Send a WhatsApp text or media message to one recipient.' It also positions itself as 'the normal way to reply to a customer,' which differentiates it from siblings like broadcast_message (multi-recipient) and send_message_fast (a faster variant). This makes it easy for an agent to select.

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?

The description says 'This is the normal way to reply to a customer,' providing some usage context. However, it does not explicitly contrast with send_message_fast or broadcast_message, nor does it mention any exclusions or prerequisites (e.g., that the device must be connected). Usage guidance is implicit rather than explicit.

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