Skip to main content
Glama
googlarz

Proton Mail Bridge MCP

by googlarz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

list_drafts

Read-only

List locally saved drafts with subject, status, timestamps, attachment metadata, and body preview to review in-progress or unsent messages.

Instructions

List all locally saved drafts with their status, subject, and timestamps. Does NOT list drafts stored only on the Proton server — use list_remote_drafts for those. Prefer get_draft when you already have a draftId and need the full content. Attachment content is omitted here (filename/type/size only) — use get_draft for the full attachment content of one draft. Each draft's body is also truncated to a short preview (bodyTruncated:true, bodyLength gives the real size) — use get_draft for the full body of one draft. Use to review in-progress or unsent messages.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum drafts to return. Defaults to 20; check hasMore and page with offset for more.
offsetNoNumber of drafts to skip, newest-updated first.
includeSentNoInclude drafts already sent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.1.37
    • addedInput schema / properties / limit
      Added value: +{
+  "description": "Maximum drafts to return. Defaults to 20; check hasMore and page with offset for more.",
+  "type": "number"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Number of drafts to skip, newest-updated first.",
+  "type": "number"
+}
  2. Addedv1.13.11
  3. Removedv1.13.11
  4. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses crucial behavioral traits: local-only scope, attachment omission (filename/type/size only), body truncation with bodyTruncated and bodyLength, and pointers to get_draft for full data. This fully sets agent expectations for outputs and limitations.

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?

Every sentence in the description earns its place; the core purpose and primary exclusion are front-loaded, followed by concise behavioral caveats and a clear usage purpose. Slightly longer than two sentences but zero redundancy.

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?

For a tool with 3 optional parameters and no output schema, the description is remarkably complete. It covers the output shape (fields, truncation flags, attachment metadata), the local/server distinction, and routes to sibling tools for full data, making it fully callable without additional lookups.

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 100%, so the schema already fully documents limit, offset, and includeSent. The description adds no new parameter-level meaning beyond what the schema provides, so the baseline of 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?

The description states a specific verb+resource ('List all locally saved drafts') and names the exact fields returned (status, subject, timestamps). It explicitly differentiates from sibling tools list_remote_drafts and get_draft, so an agent can distinguish it without opening schemas.

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?

The description gives explicit when-to-use and when-not-to-use guidance: use list_remote_drafts for server-only drafts, prefer get_draft when draftId is known or full content is needed, and use this tool to review in-progress/unsent messages. No inference required.

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

Deploy Server

Other Tools