Skip to main content
Glama
proton-mail-mcp

proton-mail-mcp

by jasen1300

unsubscribe_sender

Unsubscribes a newsletter sender via RFC 8058 one-click POST or Bridge mailto, supports dry-run detection, and falls back to an archive filter.

Instructions

Unsubscribe from a newsletter sender - PURELY DETERMINISTIC through the two safe ways (HTTPS one-click POST per RFC 8058, or mailto through your own Bridge, which needs PROTON_SMTP_ENABLED=1). No model decides; protected senders and messages with an auth failure are NEVER unsubscribed. Contacts the sender's server - do not auto-approve.

target: Message-ID (with angle brackets) OR an email address. For an
address, the newest matching message in the INBOX is used.
mode: 'auto' executes (tier 1/2), 'dry_run' only shows the detected tier.
Exactly ONE attempt per sender, ever (never a retry). If an attempt fails,
an archive filter for the sender is created as a fallback.

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": {
      "target": "<target>"
    },
    "name": "unsubscribe_sender"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoauto
targetYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it declares deterministic execution with no model decision, names the exact protocols used, states that protected senders and auth-failure messages are never unsubscribed, discloses the mailbox-level requirement PROTON_SMTP_ENABLED=1, and warns that an external server is contacted. It also exposes irreversible/idempotent traits ('Exactly ONE attempt per sender, ever (never a retry)') and the failure fallback (an archive filter is created).

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?

Front-loaded with the action and its determinism guarantee, then parameter semantics on clearly labeled lines. The opening paragraph is dense and the SMTP parenthetical is slightly awkward, but no sentence is filler given the safety stakes.

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

Completeness5/5

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

An output schema exists, so return values need not be explained; what remains for a destructive, externally-reaching action—preconditions, safety exclusions, idempotency, and failure behavior—is all covered. An agent has everything needed to decide whether and how to call it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must define both parameters, and it does: target accepts a Message-ID with angle brackets or an email address, with the resolution rule (newest matching INBOX message) spelled out, and mode's accepted values 'auto' (executes tiers 1/2) and 'dry_run' (shows detected tier only) are enumerated despite no enum in the schema. This adds substantial meaning beyond bare titles.

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 ('Unsubscribe from a newsletter sender') and immediately qualifies the mechanism (RFC 8058 one-click POST or mailto via Bridge). No sibling in the catalog does unsubscribing, so an agent can identify this tool's unique action from the first sentence alone.

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 concrete operating guidance: 'do not auto-approve', 'Contacts the sender's server', and the auto vs dry_run split for executing versus previewing the detected tier. It lacks an explicit when-to-use/when-not framing against other tools, but there is no competing sibling, and the always-one-attempt rule effectively bounds usage.

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