Skip to main content
Glama

graph_reply_mail

Replies to a specified email message, optionally to all recipients, as HTML or plain text, as an unsent draft, or from a shared mailbox.

Instructions

Reply to an email.

Args: message_id: The email message ID to reply to. body: The reply body content. When is_html is true, send explicit HTML; markdown is not converted. reply_all: Whether to reply to all recipients (default: reply to sender only). is_html: Whether to send the reply body as HTML content (default: True). Use false for plain text. as_draft: Whether to leave the reply as an unsent draft (default false). Returns the created draft instead of a sent status. mailbox: Shared mailbox address or user ID to act on. Empty targets your own mailbox. Requires the delegated Mail.*.Shared permissions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "message_id": "<message_id>",
      "body": "<body>"
    },
    "name": "graph_reply_mail"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
is_htmlNo
mailboxNo
as_draftNo
reply_allNo
message_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.10.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a fair job: it discloses that as_draft returns the created draft rather than a sent status, that HTML is sent explicitly and markdown is not converted, and that the mailbox parameter requires delegated Mail.*.Shared permissions. It omits the side-effect framing of an irreversible send and does not describe the sent-status response shape.

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?

A one-line purpose followed by a compact per-argument block; every line carries information an agent needs (defaults, permission requirement, markdown caveat). No redundant or filler prose.

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 6-parameter mutation tool with no annotations and no output schema, the description covers all inputs, defaults, a permission requirement, and the draft-vs-sent return distinction. It stops short of describing thread/subject/quoting behavior and the exact shape of the sent-status return, which leaves modest gaps for a send-side-effect tool.

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 description coverage is 0% across 6 parameters, so the description must compensate entirely, and it does: every parameter is documented with meaning, defaults, and behavior (is_html=true sends explicit HTML with no markdown conversion; empty mailbox targets your own; reply_all defaults to sender only). The added detail exceeds what the bare schema names convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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 email.' An agent knows exactly what action this performs. It does not, however, distinguish itself from adjacent siblings such as graph_send_mail, graph_create_mail_draft, or graph_forward_mail, so the sibling boundary must be inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied through parameter semantics (as_draft leaves an unsent draft instead of sending; reply_all widens recipients), which effectively signals when the tool is chosen over a send or draft-creation flow. There is no explicit statement of when to prefer this over graph_create_mail_draft or graph_send_mail, and no exclusions or prerequisites beyond the shared-mailbox permission note.

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