Skip to main content
Glama

Send Teams Chat Message

send_chat_message
Destructive

Sends Teams chat messages to an existing chat or to people by email; reuses one-on-one chats and creates group chats, returning a chat_id for follow-up messages.

Instructions

Send a Teams chat message, either in an existing chat (chat_id) or to people by email (to). With to, one person reuses your one-on-one chat with them, or starts it; two or more start a new group chat every call, so reuse the returned chat_id for follow-ups. Use chat_id '48:notes' to send to the user's self-chat (notes to self).

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": {
      "content": "<content>"
    },
    "name": "send_chat_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoComma-separated work email addresses or sign-in names of people in your organization (guests included) to message. Pass this or chat_id.
topicNoTitle for a new group chat (two or more people in to)
formatNo'text' (default) sends content as typed. 'markdown' formats it: **bold**, *italic*, `code`, ``` code blocks ```, '- ' and '1. ' lists, # headings and [links](https://…). Use markdown for steps, commands or anything with structure. Markdown is capped at 30,000 characters.
chat_idNoChat ID of an existing chat. Use '48:notes' for the user's self-chat. Pass this or to.
contentYesMessage content

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare this as a non-read-only, destructive action. The description adds valuable behavior beyond annotations: one-to-one chats are reused or started, multi-person sends create a new group chat every call, and '48:notes' targets the self-chat.

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 compact sentences, front-loaded with purpose and then operational caveats. Every sentence adds actionable detail, with no redundancy.

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 five-parameter send tool with no output schema, it covers the important behavioral edge cases and tells the agent to reuse the returned chat_id. Minor gaps remain around permissions, message visibility/editability, and explicit channel-versus-chat routing, though annotations cover the write/destructive nature.

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 the baseline is 3. The description adds meaning for 'to' beyond the schema: one person reuses or starts a 1:1 chat, while two or more start a new group chat on every call, and it reinforces the special '48:notes' chat_id.

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 Teams chat message. It also distinguishes the two targeting modes, existing chat_id versus people by email, so an agent can tell this apart from channel-message siblings.

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?

Gives clear guidance on choosing chat_id versus to, including one-person versus multi-person behavior and reusing the returned chat_id for follow-ups. It does not explicitly say when to use this instead of send_channel_message or other send_* siblings, so exclusions are missing.

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