mail-mcp

Overview Schema Source Related Servers Discussions Admin

smtp_reply_message

Reply to an existing message via SMTP (fetches original for proper threading). Before calling, show the user a full preview (To, CC, BCC, subject, rendered body, attachments) and get explicit confirmation.

Instructions

Input Schema

Name	Required	Description	Default
`body_html`	No	Reply body (HTML, optional). Separate field from `body_text`: pass the HTML itself, never wrapped in pseudo-tags like `<body_html>`; the server rejects them.
`body_text`	Yes	Reply body (plain text). Separate field from `body_html`: never concatenate the two or wrap content in pseudo-tags like `<body_text>`; the server rejects them.
`reply_all`	No	Reply to all recipients (default: false, reply to sender only)
`account_id`	No	Account identifier (defaults to `"default"`)	default
`message_id`	Yes	Stable message ID of the message to reply to
`attachments`	No	Additional file attachments (optional, base64-encoded)
`include_original_attachments`	No	Include original email's attachments in the reply (default: false)

Output Schema

Name	Required	Description
`data`	Yes	Tool-specific data payload
`meta`	Yes	Execution metadata (timestamp, duration)
`summary`	Yes	Human-readable summary of the operation outcome

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.6.0Oct 22, 2026

changedInput schema / properties / body_html / description

Previous value: -"Reply body (HTML, optional)"New value: +"Reply body (HTML, optional).\nSeparate field from `body_text`: pass the HTML itself, never wrapped\nin pseudo-tags like `<body_html>`; the server rejects them."

changedInput schema / properties / body_text / description

Previous value: -"Reply body (plain text)"New value: +"Reply body (plain text).\nSeparate field from `body_html`: never concatenate the two or wrap\ncontent in pseudo-tags like `<body_text>`; the server rejects them."

First observedv0.4.12Sep 9, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does disclose meaningful behavior: the tool performs an IMAP fetch of the original to construct In-Reply-To/References/Re: headers, and it requires user confirmation because the action sends real mail. It does not state failure behavior when the message_id is not found or whether a copy is retained.

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?

Two sentences, zero filler, with the identity/mechanism front-loaded and the safety workflow immediately after. Every clause earns its place.

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 7-parameter mutation tool with an output schema and fully documented inputs, the description covers purpose, mechanism, and the confirmation workflow. Only edge-case behavior (missing original, account resolution failures) is left unaddressed.

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 coverage is 100% and each parameter (reply_all, include_original_attachments, attachments, body_html/body_text separation rules) is already documented in the schema. The description adds no parameter-level detail, so the baseline 3 applies.

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?

States a specific verb and resource ('Reply to an existing message') plus transport ('via SMTP') and the mechanism that makes it distinct ('fetches original for proper threading'). This clearly separates it from smtp_send_message, smtp_forward_message, and draft_create in the sibling list.

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 an explicit procedural precondition: show a full preview of To/CC/BCC/subject/body/attachments and obtain explicit user confirmation before invoking. What's missing is explicit routing versus alternatives (e.g., when to reply directly vs. create a draft with draft_create).

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