Skip to main content
Glama
access-ctrl

@lnwebworks/outlook-mcp-server

by access-ctrl

create_email_draft

Create an Outlook draft email with recipients, subject, body, and attachments up to 25MB, saving it to the Drafts folder for review before sending.

Instructions

Create a standalone draft email in Outlook Drafts folder for review before sending. Supports file attachments up to 25MB combined.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNoComma-separated CC email address(es)
toYes
bccNoComma-separated BCC email address(es)
bodyYes
mailboxNoTarget Outlook email address / mailbox. Defaults to primary configured user email if omitted.
subjectYes
attachmentsNoAbsolute file paths under /opt/data to attach. Up to 3MB combined attaches instantly; over 3MB (up to 25MB combined) is uploaded in chunks automatically — no difference in how you call this, just slower for the larger case. Over 25MB combined is rejected.
conversationIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.2.3

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the behavioral burden. It states that a draft is created in Outlook Drafts, that it is not sent immediately, and that attachments up to 25MB are supported. However, it does not disclose return value, persistence behavior, side effects, or error conditions.

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?

The description is two sentences with no filler. The primary action and location are front-loaded, and the attachment limit is summarized efficiently.

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

Completeness2/5

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

For a tool with 8 parameters, no annotations, no output schema, and several closely related sibling tools, this description is too thin. It does not explicitly differentiate from create_reply_draft or send_email, explain required parameters, or clarify how conversationId fits with 'standalone'.

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

Parameters2/5

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

Schema description coverage is only 50%, and the description adds no parameter-level meaning beyond what the schema already provides. Required fields like to, subject, and body remain undocumented, and conversationId is not explained; the only added detail is an attachment-size summary already present in the schema.

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 uses a specific verb ('Create'), a clear resource ('standalone draft email'), and a precise location ('Outlook Drafts folder'). The qualifier 'standalone' helps distinguish it from reply-draft tools like create_reply_draft.

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?

'For review before sending' gives a clear usage context: use this when a draft should be prepared but not immediately sent. 'Standalone' also differentiates it from reply/thread-based draft creation, though it does not explicitly name sibling tools or state when not to use it.

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