Skip to main content
Glama
mail-mcp-server

mail-mcp-server

plan_create_send_as

Plan adding a send-as address to a Gmail mailbox without changing anything. Preview affected items and get a plan_id before executing; Gmail then requires clicking a confirmation link.

Instructions

Dry run: changes nothing. Returns what would be affected and a plan_id for execute_plan. Show the user the summary before asking whether to execute. Add an address the mailbox can send as (Gmail's "Send mail as"). Gmail emails the address a confirmation link that has to be clicked before it can be used.

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": {
      "mailbox": "<mailbox>",
      "email": "<email>"
    },
    "name": "plan_create_send_as"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailYes
mailboxYesA connected mailbox address (see list_mailboxes)
reply_toNo
signatureNoHTML signature
display_nameNoName recipients see
treat_as_aliasNoGmail's "treat as an alias"; default true, as in Gmail

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the load and does it well: 'Dry run: changes nothing' discloses the non-mutating nature, it names the return payload (what would be affected plus a plan_id), and it surfaces the non-obvious external side effect that Gmail emails a confirmation link which must be clicked before the address works. Missing only permission/scope or duplicate-address handling.

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

Conciseness4/5

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

Four short sentences, each carrying a distinct fact (safety, return value, UI flow, external confirmation step). Slightly jumbled ordering, since the actual purpose appears after the dry-run boilerplate, but nothing is wasted or padded.

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 6-parameter mutation-planning tool with no output schema, the description covers safety, return shape, follow-up tool and the confirmation-email consequence. An agent can call it correctly and knows what to do next; only edge cases like address-already-exists are unaddressed.

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 67%, so email, mailbox, reply_to, signature, display_name and treat_as_alias are partly documented in the schema. The description adds no per-parameter meaning — nothing about what reply_to or treat_as_alias do in the plan context — so it sits at the baseline for a mostly-covered schema.

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: 'Add an address the mailbox can send as (Gmail's "Send mail as")'. This distinguishes it from plan_update_send_as and plan_delete_send_as by verb alone, and the dry-run framing makes clear it is the planning counterpart of the add operation.

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?

Explicitly routes the agent: 'Returns a plan_id for execute_plan' and 'Show the user the summary before asking whether to execute'. That is a clear when-and-how sequence. It stops short of naming exclusions (e.g., use plan_update_send_as instead when the address already exists), so not a 5.

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