Skip to main content
Glama
mail-mcp-server

mail-mcp-server

plan_unsubscribe

Preview which senders will be unsubscribed via their List-Unsubscribe headers and get a plan_id for execution; no mailbox changes occur until you approve.

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. Unsubscribe from senders using their own List-Unsubscribe header: one-click POST, else a mailto message to the header's address. Senders with only a link, or nothing, are reported for the user to handle.

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>",
      "senders": "<senders>"
    },
    "name": "plan_unsubscribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
mailboxYesA connected mailbox address (see list_mailboxes)
sendersYesSender addresses, at most 100

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that nothing is mutated, what is returned (affected items plus plan_id), the outbound protocol used per sender (HTTP POST vs mailto), and which senders are skipped. It stops short of detailing the plan's lifetime/expiry or what the summary fields contain, which leaves a small gap for a two-phase tool.

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?

The dry-run/no-side-effect guarantee is front-loaded in the first clause, followed by the plan_id handoff and the user-confirmation instruction, then mechanism detail. Every sentence adds distinct operational information; nothing is filler.

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?

With no output schema, the description does explain the return payload (what would be affected, a plan_id, and unhandleable senders) and the two-step workflow. Only the shape of the summary object and plan validity window are unstated, which is a minor omission for a low-complexity 2-parameter tool.

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 100%, so mailbox and senders are already documented, including the 100-sender cap and the list_mailboxes pointer. The description adds only implied semantics (senders must be addresses whose headers it will inspect), so the baseline 3 is appropriate.

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?

Names a specific action (unsubscribe from senders), the exact mechanism (List-Unsubscribe header: one-click POST, else mailto), and frames the tool as a dry run that produces a plan_id for execute_plan. It is clearly distinguishable from execute_plan and from the other plan_* siblings.

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 states this is a dry run that changes nothing, tells the agent to hand the plan_id to execute_plan, and instructs showing the summary and confirming with the user before execution. It also covers the fallback case: senders with only a link or no header are reported for the user to handle.

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