Skip to main content
Glama
gmail-mcp
by gchallen

send_draft

Send an existing Gmail draft as-is by its draft ID, returning the sent message and thread IDs. Use it to deliver a prepared draft without editing or rewriting its content.

Instructions

Send an existing draft as-is. Returns the sent message ID and thread ID.

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": {
      "draftId": "<draftId>"
    },
    "name": "send_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
draftIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.9.2

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the write/external-effect profile is known. The description usefully adds the return values (message ID, thread ID) since no output schema exists, and 'as-is' implies no edits are applied, but it omits what happens to the draft afterwards (consumed/replaced) and any permission requirements.

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 short, front-loaded sentences with zero filler: action first, return values second.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with no annotations gaps, the description covers the action and the return shape. It is still thin on post-send side effects and parameter meaning, which matters for an irreversible send.

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 0% and the single property draftId carries no description. The description never explains that draftId identifies the draft to send or what format it takes, though the field name is fairly self-evident.

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 an existing draft') and the 'as-is' qualifier separates it from composing-and-sending siblings like send_message and from create_draft/update_draft. It does not explicitly name those siblings, but the scope is unambiguous.

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?

Usage is only implied: it acts on an existing draft, so an agent can infer it must first have a draftId. No statement of when to prefer send_message or reply instead, and no note on what happens when the draft is invalid or already sent.

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