Skip to main content
Glama
Pombus MCP Server

Pombus MCP Server

Official

Send draft

send_draft
DestructiveIdempotent

Sends a previously created email draft to external recipients; call only after human review because delivery cannot be undone.

Instructions

Send a previously created draft. This delivers email to external recipients and cannot be undone. Only call after a human has reviewed the draft.

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>",
      "draft_id": "<draft_id>"
    },
    "name": "send_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
draft_idYes
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

A3.8/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the danger profile is structurally known. The description earns credit for adding two things beyond that: delivery goes to external recipients and the action cannot be undone, plus a human-review precondition. It omits post-send state (is the draft consumed, is it retryable) which matters given idempotentHint=true on a 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?

Three short sentences, each doing distinct work: what it does, what the risk is, and the prerequisite. Zero filler and the action is front-loaded.

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 two-parameter mutation with no output schema, the definition covers the essentials an agent needs: it is destructive, it reaches external recipients, and it requires prior human review. The remaining gap is draft_id's semantics and what happens to the draft after sending, which is minor against annotations that already flag destructiveness.

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 coverage is 50%: inbox_id is documented in the schema with a scoping/rejection note, while draft_id has no description anywhere. The phrase 'previously created draft' only loosely implies draft_id's provenance and adds no format or sourcing detail. With the schema carrying half the burden, the baseline 3 applies.

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?

States a specific verb and resource ('Send a previously created draft'), which cleanly separates it from create_draft. It stops short of distinguishing itself from the send_message sibling, so an agent must infer that this one operates on an existing draft rather than composing new content.

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 a clear precondition for invocation: 'Only call after a human has reviewed the draft,' which is a meaningful gate for an irreversible action. It does not name or exclude any alternative tool (e.g. send_message) for cases where no draft exists, so the routing guidance is incomplete but the primary usage context is explicit.

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