Skip to main content
Glama
ChatPush MCP Server

ChatPush MCP Server

Official
by ChatPush

Delete delivery

delete_delivery
DestructiveIdempotent

Deletes a delivered WhatsApp or Telegram message on all recipient devices, letting you unsend or recall messages sent via ChatPush. Works only for messages with Delivered status; SMS cannot be deleted.

Instructions

Delete a sent message from WhatsApp or Telegram (tdlib). Only works for messages with final 'Delivered' status. Deletion occurs on all recipient devices.

Only messages sent through ChatPush via the tdlib or whatsapp channels can be deleted; SMS cannot. Use it when the user asks to unsend or recall a message.

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": {
      "delivery_id": "<delivery_id>"
    },
    "name": "delete_delivery"
  }
}

Input Schema

NameRequiredDescriptionDefault
delivery_idYesID of the delivered message to delete (delivery.id from send_message).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

The description discloses the key destructive consequence beyond the annotations: deletion occurs on all recipient devices and cannot be scoped to a single device. That is valuable context even though destructiveHint=true already warns of mutation. It does not cover failure behavior (e.g. what happens if the status is not final) or response shape, keeping it just short of 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.

Conciseness5/5

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

Three short sentences, front-loaded with what it does, then the preconditions, then the trigger phrasing. Every sentence adds a constraint or a routing cue; nothing is redundant padding.

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 single-parameter destructive tool with full annotations and full schema coverage, this covers the missing pieces: channel limits, status precondition, and the cross-device blast radius. An agent has enough to decide correctly whether to call it.

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% and the single parameter already documents that delivery_id comes from send_message's delivery.id. The description adds no extra meaning about the identifier, so the baseline 3 applies.

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 ('Delete a sent message') plus the channels covered (WhatsApp/Telegram via tdlib). It also names the status precondition ('final Delivered status'), which distinguishes it from send_message and the get_* siblings.

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?

Explicitly says when to use it ('when the user asks to unsend or recall a message') and when not to: only final-Delivered messages, only tdlib/whatsapp channels, SMS cannot be deleted. The exclusion conditions are stated outright rather than left to inference.

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