Skip to main content
Glama

graph_send_message

Send email via Microsoft Graph API for personal Hotmail/Outlook.com accounts where SMTP is blocked, with preview confirmation, attachments, CC/BCC, and reply threading.

Instructions

Send email via Microsoft Graph API (required for personal hotmail/outlook.com accounts where SMTP is blocked). Before calling, show the user a full preview (To, CC, BCC, subject, rendered body, attachments) and get explicit confirmation.

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": {
      "to": "<to>",
      "subject": "<subject>"
    },
    "name": "graph_send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCC recipients (optional, max 50)
toYesRecipient email addresses (1..50)
bccNoBCC recipients (optional, max 50)
subjectYesEmail subject (1..998 characters)
reply_toNoReply-To address (optional)
body_htmlNoHTML body (at least one of body_text or body_html required). Separate field from `body_text`: pass the HTML itself, never wrapped in pseudo-tags like `<body_html>`; the server rejects them.
body_textNoPlain text body (at least one of body_text or body_html required). Separate field from `body_html`: never concatenate the two or wrap content in pseudo-tags like `<body_text>`; the server rejects them.
account_idNoAccount identifier (defaults to `"default"`)default
referencesNoReferences header for threading (optional)
attachmentsNoFile attachments (optional, base64-encoded)
in_reply_toNoIn-Reply-To message ID for threading (optional)
save_to_sentNoSave to Sent Items folder (default: true)

Output Schema

NameRequiredDescriptionDefault
dataYesTool-specific data payload
metaYesExecution metadata (timestamp, duration)
summaryYesHuman-readable summary of the operation outcome

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.0
    • changedInput schema / properties / body_html / description
      Previous value: -"HTML body (at least one of body_text or body_html required)"New value: +"HTML body (at least one of body_text or body_html required).\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: -"Plain text body (at least one of body_text or body_html required)"New value: +"Plain text body (at least one of body_text or body_html required).\nSeparate field from `body_html`: never concatenate the two or wrap\ncontent in pseudo-tags like `<body_text>`; the server rejects them."
  2. First observedv0.4.12

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true, non-idempotent and non-destructive; the description adds genuinely extra behavior — that real mail leaves the system only after a full user-visible preview and explicit confirmation. It does not cover rate limits, failure modes, or what happens when account_id points at a non-personal/misconfigured account, but the confirmation protocol is the most important operational trait and it is disclosed.

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, no waste, and the selection criterion is front-loaded before the procedural requirement. Nothing here is padding.

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?

An output schema exists, so return values need no explanation, and the 12 parameters are fully documented in the schema. What remains thin is multi-account behavior (account_id defaults to "default") and threading parameters (in_reply_to/references) — the descriptions of reply/forward siblings suggest those paths matter, yet this tool's description is silent on them.

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 the baseline is 3. The description's only parameter-adjacent content is enumerating the fields to preview (To, CC, BCC, subject, rendered body, attachments), which reinforces but adds no new semantics about formatting, threading, account selection, or limits.

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 (send email) plus the transport (Microsoft Graph API), and immediately scopes it to the case that selects it over SMTP-based siblings: personal hotmail/outlook.com accounts where SMTP is blocked. An agent can distinguish this from smtp_send_message and ews_send_message without opening either schema.

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 a clear positive selection condition (personal Microsoft accounts / SMTP-blocked environments) and a mandatory pre-call workflow (full preview then explicit user confirmation). It stops short of explicitly naming smtp_send_message or ews_send_message as the fallback for other accounts, so routing for non-hotmail cases is left to inference.

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