Skip to main content
Glama

Send chat message

send_chat_message

Write a message in a chat, as yourself — as the screen sends it: the chat's people see it at once, and it is told by push and by letter to whoever it calls: in a direct chat the other person, in a group or a project's chat only who it mentions ([~username], the handle list_users gives) or answers (replyTo). An agent of the chat answers when mentioned ([~agent:product]) or replied to, and in a chat with an agent every message is a question to it. A project's chat takes a message from whoever may comment in the project. Answers with 'notified' (who this actually tells, and why: direct, mention, reply — never yourself), 'unresolvedMentions' (what looked like a mention and told nobody, with a reason: unknown, inactive, self, not_in_chat, or an agent's) and 'agents' (the agents it called and their requests). A wrong handle is kept as written and never refused, so that list is the only sign it did not land. With 'quote' (and replyTo), it answers those words of the message: they are kept with yours as quoted, and the message's author is told as for any reply. Text only — files are sent from the screen.

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": {
      "chatId": "<chatId>",
      "body": "<body>"
    },
    "name": "send_chat_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesThe message, Markdown — with $…$ formulas and [~username] mentions. At most 32 KB.
quoteNoSome words of the replyTo message this one quotes, exactly as they read there — shown above your message, linked to them. Needs replyTo; at most 2000 characters. Omit to answer the whole message.
chatIdYesThe chat's id, as list_chats gives it.
replyToNoThe message of this chat this one answers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / quote
      Added value: +{
      +  "default": null,
      +  "description": "Some words of the replyTo message this one quotes, exactly as they read there — shown above your message, linked to them. Needs replyTo; at most 2000 characters. Omit to answer the whole message.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations only declare it is a non-read-only, non-destructive, non-open-world write; the description goes far beyond that. It discloses the notification fan-out model (direct vs. mention vs. reply vs. project chat), that replies trigger agents, that a wrong handle is silently kept and only surfaces in unresolvedMentions, and the exact meaning of the notified/unresolvedMentions/agents response fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Information density is high with little outright filler, but it is a single sprawling paragraph mixing notification semantics, permission rules, mention resolution, and quoting. Ornate phrasing such as "told by push and by letter" and "whoever it calls" obscures rather than front-loads the delivery model.

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?

There is no output schema, and the description compensates by explaining exactly what notified, unresolvedMentions, and agents return and why. Combined with permission prerequisites, size limits, text-only restriction, and quote behavior, an agent has enough to call this correctly and interpret the result.

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 baseline is 3, but the description adds real meaning: mention syntax [~username] tied to list_users, agent handles as [~agent:product], and the constraint that quote is answered only when replyTo is present and must match the target's words exactly. This supplements rather than repeats the schema.

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?

Opens with a specific verb and resource: "Write a message in a chat, as yourself," and clarifies scope with "Text only — files are sent from the screen," which implicitly separates it from attachment tools. It never names edit_chat_message or delete_chat_message, so an agent must infer the boundary between sending and later editing, but the core action is unmistakable.

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?

Useful preconditions are embedded, such as "A project's chat takes a message from whoever may comment in the project" and the rule that agents are invoked by mention or reply. However, there is no explicit when-to-use/when-not guidance or named alternative (e.g., use edit_chat_message to change a message already sent), so routing 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