Skip to main content
Glama
googlarz

Proton Mail Bridge MCP

by googlarz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

get_draft

Read-only

Retrieve a local draft's full content using its draft ID to review or verify before sending. Attachment metadata is returned unless includeAttachmentContent is set to true for raw base64 data.

Instructions

Fetch the full content of a single locally saved draft by its draftId. Use to read or verify a draft before sending or updating. Prefer list_drafts to discover draftIds first. Does NOT fetch drafts from the Proton server — use list_remote_drafts for those. Attachments are metadata only (filename/contentType/size, no base64 content) by default — set includeAttachmentContent:true if you actually need the raw bytes back (e.g. to re-attach them elsewhere); a large attachment's base64 content can be hundreds of thousands of tokens.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
draftIdYesDraft id returned by create_draft, list_drafts, or a create_*_draft call.
includeAttachmentContentNoReturn each attachment's full base64 content instead of just its metadata. Off by default — see the tool description.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.37
    • addedInput schema / properties / includeAttachmentContent
      Added value: +{
+  "default": false,
+  "description": "Return each attachment's full base64 content instead of just its metadata. Off by default — see the tool description.",
+  "type": "boolean"
+}
  2. Addedv1.13.11
  3. Removedv1.13.11
  4. Changed1 schema field changedv0.1.2
    • addedInput schema / properties / draftId / description
      Added value: +"Draft id returned by create_draft, list_drafts, or a create_*_draft call."
  5. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already signal readOnlyHint=true, so no mutation is expected. The description goes further by revealing that only locally saved drafts are fetched, that attachments return metadata only by default, that includeAttachmentContent:true is needed for raw bytes, and that large base64 attachments can be extremely token-heavy. These are genuine behavioral details not present in the structured fields.

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 description is front-loaded with the core operation and purpose, and every sentence carries useful information. The final sentence is long and packs several clauses together, but it all earns its place, especially the token-size warning. Slightly tighter punctuation would make it cleaner.

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 simple read tool with one required parameter, a readOnly annotation, and no output schema, the description is complete enough: it covers discovery, local vs. remote scope, attachment default behavior, and the rare scenario requiring raw attachment bytes. An agent has everything needed to invoke and reason about the result.

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 coverage is 100%, but the description still adds meaning beyond it: draftId is clarified as coming from create_draft, list_drafts, or create_*_draft calls, and includeAttachmentContent is tied to a concrete tradeoff (metadata vs. raw base64 content) with a token-cost warning. The schema itself even points to the description for fuller guidance.

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 names a specific operation and resource: fetch the full content of a single locally saved draft by draftId. It also distinguishes itself from related tools such as list_drafts and list_remote_drafts, so an agent can tell exactly which tool this is.

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?

It explicitly states when to use the tool ('read or verify a draft before sending or updating'), tells the agent to prefer list_drafts to discover draftIds first, and gives a clear alternative (list_remote_drafts) for server-side drafts. This is direct routing guidance rather than implied usage.

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