Skip to main content
Glama
Sign In

MentionAgent

by ai.mentionagent
OverviewDiscussionsAdmin

Reply to a thread

send_reply
Destructive

SENDS REAL EMAIL. Replies to one conversation. The recipient and the subject come from the thread and cannot be set here, so this can only ever answer the person already in it, plus anyone at their own organisation they copied on their latest message. Read the thread with get_thread first, and show the person what you are about to send before sending it.

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>",
      "body": "<body>"
    },
    "name": "send_reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesThe reply. Plain text is fine; line breaks are kept.
conversationIdYesFrom list_inbox or get_thread.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description adds real value beyond them by explaining recipient scope, the fact the recipient and subject are fixed by the thread, and that copies to the sender's own organisation may be reached. That is the exact consequence an agent needs before firing an irreversible send.

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?

Front-loads the highest-stakes fact ('SENDS REAL EMAIL') and then orders the constraints, prerequisite, and confirmation step. Every sentence adds information an agent would otherwise have to guess.

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 2-parameter, irreversible send tool with no output schema, the description supplies the missing pieces: side-effect severity, recipient constraints, prerequisite read, and human confirmation. Nothing needed to invoke it safely is absent.

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, but the description adds meaning the schema cannot: recipient and subject are deliberately absent as parameters and cannot be overridden. It also ties conversationId implicitly to get_thread, reinforcing the schema's 'From list_inbox or get_thread' note.

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 (replies) and resource (one conversation), and the opening 'SENDS REAL EMAIL' distinguishes it from the draft-oriented siblings without ambiguity. An agent can tell exactly what this does and how it differs from draft_reply or get_thread.

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 an explicit prerequisite ('Read the thread with get_thread first') and a confirmation workflow ('show the person what you are about to send before sending it'). It does not name draft_reply as the explicit alternative for a non-sending preview, so routing guidance is clear but not exhaustive.

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

All MentionAgent toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources