Skip to main content
Glama
proton-mail-mcp

proton-mail-mcp

by jasen1300

ai_triage

Rates messages for spam/phishing, category, and priority, then suggests actions; previews by default and applies approved moves only with safety checks.

Instructions

AI triage: rates messages (spam/phishing, category, priority) and suggests actions; apply=True executes them (default: preview only).

Safety: spam/phishing is moved to the spam folder (reversible) only with a
failed SPF/DMARC check, never deleted; protected and pinned senders and
low-confidence verdicts are never moved. Combines the auth check, the
Claude verdict and your policy (get_ai_policy/set_ai_policy). Needs
ANTHROPIC_API_KEY. Do not auto-approve apply=True.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ai_triage"
  }
}

Input Schema

NameRequiredDescriptionDefault
applyNo
limitNo
folderNoINBOX
all_mailNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses that spam/phishing is moved (not deleted) and is reversible, that movement only occurs on a failed SPF/DMARC check, that protected/pinned senders and low-confidence verdicts are never moved, and that ANTHROPIC_API_KEY is required. These are exactly the side effects, preconditions, and safety rails an agent needs before setting apply=True.

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 purpose comes first, then safety constraints, then policy integration and the API-key prerequisite — a sensible front-loaded order with no filler sentences. Density is high but a few clauses (e.g. 'Combines the auth check, the Claude verdict and your policy') could be tightened without losing meaning.

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 tool with real side effects, the description covers behavior, safety gating, reversibility, and dependencies thoroughly, and an output schema exists so return values need no explanation. The remaining hole is the three undocumented input parameters, which matters because folder and all_mail change which messages are even triaged.

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 description coverage is 0%, so the description must supply meaning, and it only does so for 'apply' — explaining that True executes the suggested actions while the default is preview. The limit, folder, and all_mail parameters are never mentioned, leaving three of four inputs undocumented anywhere.

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: it rates messages on spam/phishing, category, and priority, and suggests actions, with apply=True executing them. The read-vs-write split is made explicit ('default: preview only'). It stops short of naming how it differs from close siblings like ai_analyze_email or surface_priority, so the agent must infer the boundary.

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 clear when-to-use context: run with default preview first, and 'Do not auto-approve apply=True' is an explicit caution against unattended execution. It also points to get_ai_policy/set_ai_policy as the policy source. It does not state when to choose this over the sibling analysis tools, leaving that comparison implicit.

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