Skip to main content
Glama

Send message as operator

dosai_send_operator_message
Destructive

Send a message to a real client in WhatsApp, Instagram or Telegram, as a human operator. Works for a WhatsApp group dialog too (kind=group): the message goes into the group from the owner's number and every member sees it. This is visible to real people and cannot be unsent, so confirm the wording with the user before calling. No dialog for that phone yet? Open one with open_conversation first. The result says delivered: true when WhatsApp took the message, or delivered: "unknown" when WhatsApp did not confirm within 15 seconds: the message may well have gone out (it usually has), so call it neither sent nor failed; repeat the same call within 5 minutes (safe: it returns the first attempt's outcome and never sends twice) or read its status in get_messages a minute later. A refusal (number reconnecting, night rule, unsubscribed) comes back as an error that says the message was NOT delivered.

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": {
      "project_id": "<project_id>",
      "conversation_id": "<conversation_id>",
      "text": "<text>"
    },
    "name": "dosai_send_operator_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesExactly what the client will see.
project_idYesFrom dosai_list_projects.
conversation_idYesFrom dosai_list_conversations.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / conversation_id / description
      Previous value: -"Conversation id, as returned by dosai_list_conversations."New value: +"From dosai_list_conversations."
  2. Changed2 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / project_id / description
      Previous value: -"Project id, as returned by dosai_list_projects."New value: +"From dosai_list_projects."
  3. Changed2 schema fields changed
    • removedInput schema / properties / conversation_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedInput schema / properties / project_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructive=true and openWorldHint=true, but the description goes well beyond them: it discloses human visibility, irreversibility, the delivered/unknown timeout branch with a 15-second window and 5-minute idempotent retry, and the meaning of refusal errors. Minor deduction because the description never states which account or permissions are used beyond 'the owner's number' and gives no pagination/response-shape context.

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 critical warnings — human-visible, cannot be unsent, confirm wording — are front-loaded, and every clause carries operational meaning. It is a dense single block of prose, though, with the timeout/retry detail packed mid-paragraph where it is easy to skim past.

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?

For a destructive, open-world send with no output schema, the definition supplies the outcome semantics (delivered true vs "unknown"), the timeout duration, idempotent retry behavior, and error-based refusal signals. An agent has everything needed to call this correctly and interpret the result without guessing.

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 project_id, conversation_id and text are already documented, with text's 'exactly what the client will see' note duplicated in the schema. The description adds no syntax or constraint detail for these three parameters; the 'kind=group' mention refers to dialog type rather than any listed parameter, which could momentarily confuse an agent scanning the schema.

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 ('send a message to a real client') and scopes it by channel (WhatsApp, Instagram, Telegram) plus the group-dialog variant. An agent can distinguish it from dosai_send_operator_media or dosai_send_whatsapp_template by the plain-text human-operator framing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use guidance includes the prerequisite ('no dialog yet? open one with open_conversation first'), the pre-call requirement to confirm wording with the user, and a named alternative for status checks (get_messages). It also prescribes the retry action and its safety bound, so no decision is left to inference.

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