Skip to main content
Glama
icloud-mcp

icloud-mcp

by adamzaidi

save_draft

Save a draft email to your iCloud Drafts folder without sending it, so you can edit and send it later from Mail.app or iCloud.com.

Instructions

Save a draft email to your iCloud Drafts folder without sending it. Supports plain text, HTML, or both. The draft can be edited and sent later from Mail.app or iCloud.com.

Input Schema

NameRequiredDescriptionDefault
ccNoCC recipient(s)
toYesIntended recipient(s), comma-separated or array
bccNoBCC recipient(s)
bodyNoPlain text body (used as fallback when html is also provided)
htmlNoHTML body. If provided without body, plain text is auto-generated. If provided with body, saves multipart/alternative.
accountNoAccount whose Drafts folder to save into (e.g. "work", "personal", "school"). Defaults to iCloud.
subjectYesEmail subject
inReplyToNoMessage-ID of the email being replied to — sets In-Reply-To header for threading
referencesNoSpace-separated Message-IDs for the References header — enables full thread linking

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.8.0
    • changedInput schema / properties / account / description
      Previous value: -"Account whose Drafts folder to save into (e.g. \"umd\", \"personal\", \"alt\"). Defaults to iCloud."New value: +"Account whose Drafts folder to save into (e.g. \"work\", \"personal\", \"school\"). Defaults to iCloud."
  2. First observedv2.5.1

TDQS

A4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full disclosure burden. It usefully discloses that the draft is not sent and can be edited/sent later, and that plain text, HTML, or both are supported. But it omits authentication needs, whether an existing draft is overwritten or a new one is always created, error behavior, and return values, leaving significant gaps for a write operation.

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?

Three sentences with the core purpose front-loaded, followed by supported formats and later-editability. No wasted words and the structure is easy to parse.

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?

Given 100% schema coverage and no output schema, the description covers the essential purpose, non-sending behavior, format support, and post-save editing. A slight gap remains: it does not clarify that the account parameter can target non-iCloud accounts, nor does it explicitly relate the tool to compose_email for sending workflows.

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 all nine parameters are already documented in the input schema. The description mentions plain text/HTML/both and the iCloud Drafts folder, but adds little beyond what the schema already explains, especially regarding the body/html fallback behavior.

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 and resource: 'Save a draft email to your iCloud Drafts folder without sending it.' The explicit 'without sending it' distinguishes this from send-oriented siblings like compose_email, reply_to_email, and forward_email. It is clear what the tool does and how it differs from sending tools.

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?

It gives clear context for use: save rather than send, and the draft can be edited and sent later. However, it does not explicitly name an alternative tool or state when not to use this tool, so it falls short of the top score.

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