Skip to main content
Glama

Send Alibaba message

alibaba_send_message
Destructive

Sends a message to an Alibaba conversation by conversation ID after explicit user approval, without switching the open chat.

Instructions

Get the user's explicit approval before sending. Show the exact conversation and the exact message text, wait for a clear yes, and only then call alibaba_send_message. Do not send, rewrite-and-send, or retry a send without a new approval. Sends by conversation id through the messenger page and does not switch the open chat. Requires read/write access. This sends a real Alibaba 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": {
      "conversationId": "<conversationId>",
      "text": "<text>"
    },
    "name": "alibaba_send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
conversationIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

A4.3/5.0
Behavior5/5

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

The annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the safety profile is known. The description adds value beyond that: it confirms a real message is delivered, that read/write access is required, and that the open chat is not switched as a side effect. The mandated approval gate is behavioral detail found nowhere in the structured fields.

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 approval gate is correctly front-loaded and every sentence carries a rule the agent needs. The idea of approval is restated in the second and third sentences ('wait for a clear yes' then 'without a new approval'), which is slightly redundant but arguably reinforces a safety-critical constraint.

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 should ideally say what a successful send returns, and it does not; nor does it describe failure behavior. Everything an agent needs to decide whether and how to invoke it, including the permission requirement and side effects, is present, so the omission is minor for a two-parameter tool.

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 0% for both required parameters, so the description must partially compensate. It clarifies that conversationId targets the conversation and that text is the literal message body to display for approval, but it gives no guidance on where conversationId comes from (e.g., alibaba_list_conversations) or on formatting, so the gap is only partly filled.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('sends a real Alibaba message' by 'conversation id through the messenger page') and adds a distinguishing behavioral trait: it 'does not switch the open chat.' That is enough to separate it from the read-only siblings like alibaba_get_conversation, though no sibling is named explicitly.

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?

It states exactly when to call: only after showing the exact conversation and exact message text and receiving a clear yes. It also states when not to call: 'Do not send, rewrite-and-send, or retry a send without a new approval.' The preconditions and prohibitions are explicit and leave nothing to inference.

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