Skip to main content
Glama
mail-mcp-server

mail-mcp-server

plan_set_auto_forward

Plan enabling or disabling auto-forwarding for every incoming message to a confirmed address. Returns a dry-run summary and plan_id so users can review affected settings before execution.

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. Turn auto-forward of every incoming message on (to a confirmed forwarding address) or off. The summary names the destination in full.

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>",
      "enabled": "<enabled>"
    },
    "name": "plan_set_auto_forward"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailNoDestination; required to turn it on
enabledYes
mailboxYesA connected mailbox address (see list_mailboxes)
dispositionNoWhat happens to the original; default leaveInInbox

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations present, the description carries the full burden and does so well: it discloses that nothing is changed, what is returned (affected items summary plus plan_id), the user-confirmation requirement, and the constraint that the destination must be a confirmed forwarding address. Remaining unknowns (plan expiry, cross-mailbox behavior) are minor for a dry-run tool.

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?

The most important fact — 'Dry run: changes nothing' — is front-loaded, and the sentences are short and directive. The closing sentence about the summary naming the destination is somewhat redundant with the earlier summary language but still carries a useful check against silent mis-forwarding.

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?

No annotations and no output schema, so the description must cover return behavior, which it does by describing the summary and plan_id. It is largely complete for a two-step plan/execute tool, though it does not say whether plan_id expires or what happens when email is omitted while disabling.

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 75%, so the schema documents most fields; the description still adds real value by stating that the destination address is required to turn forwarding on and must be confirmed, a cross-parameter condition the schema does not express. The disposition enum's meaning is left entirely to the 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 — turning auto-forwarding of every incoming message on or off — and frames the operation as a dry-run that produces a plan rather than a change. The pairing with execute_plan distinguishes it cleanly from the sibling that actually mutates state.

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 says to show the user the summary and ask before executing, and names execute_plan as the follow-up tool with the plan_id. The dry-run framing also tells the agent when NOT to expect changes, so the plan→execute workflow is unambiguous.

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