Skip to main content
Glama
Pombus MCP Server

Pombus MCP Server

Official

Send message

send_message
Destructive

Compose and send a new email directly to external recipients without a draft; use only when direct-send is granted, as delivery cannot be undone.

Instructions

Compose and send a NEW message directly, without a draft. This delivers email to external recipients and cannot be undone. Prefer create_draft -> send_draft so a human reviews before sending; this tool exists only for keys the human granted direct-send.

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": {
      "inbox_id": "<inbox_id>",
      "to": "<to>"
    },
    "name": "send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toYes
bccNo
textNo
subjectNo
inbox_idYesAn inbox id previously returned by list_inboxes. The server rejects any id outside this key's scope.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is structured. The description still adds non-redundant context: delivery goes to external recipients, the action cannot be undone, and it is gated on a direct-send key grant. It stops short of saying what happens on partial failure or whether bcc is stripped, but it goes meaningfully beyond the annotations.

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?

Two sentences, front-loaded with the action and the irreversibility warning, then the routing guidance. No filler or restated title.

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 destructive, non-idempotent send with no output schema, the description covers irreversibility, the human-review alternative, and the key-scope prerequisite. The remaining gap is recipient/body parameter guidance, which an agent calling this correctly would likely want.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 17% — just inbox_id is documented. The description adds no meaning for the other five parameters: it never says 'to' accepts multiple recipients, whether text is the plain-text body, or whether HTML is unsupported. With low coverage the description was expected to compensate and does not.

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 ('Compose and send a NEW message directly, without a draft') and immediately separates itself from the draft-based siblings. An agent can distinguish this from create_draft/send_draft without opening either schema.

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 names the preferred alternative ('Prefer create_draft -> send_draft so a human reviews before sending') and the precise condition under which this tool applies ('only for keys the human granted direct-send'). Both the when-to-use and the when-to-avoid are stated, not implied.

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