Skip to main content
Glama

Send email

send_message

Compose and send a new Outlook email immediately, with recipients, subject, body, and attachments, saving a copy in Sent Items. Use create_draft first when the message needs review.

Instructions

Compose and immediately send a new email (a copy is saved in Sent Items). Use create_draft instead if the user wants to review it first.

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>",
      "body": "<body>"
    },
    "name": "send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCc recipients: email addresses, either "jane@contoso.com" or "Jane Doe <jane@contoso.com>"
toYesRecipients: email addresses, either "jane@contoso.com" or "Jane Doe <jane@contoso.com>"
bccNoBcc recipients: email addresses, either "jane@contoso.com" or "Jane Doe <jane@contoso.com>"
bodyYesMessage body
subjectYesSubject line
bodyFormatNoBody format: "text" (default) or "html"
importanceNoMessage importance
attachmentsNoFiles to attach

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the description adds the material nuance: sending is immediate and irreversible once invoked, and a copy lands in Sent Items. It does not mention permission requirements or any rate/size limits on the up-to-20 attachments, so it stops short of full behavioral disclosure.

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 filler. The purpose and its irreversible side effect are front-loaded, and the alternative follows as the qualifier.

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 an 8-parameter, all-documented send tool with no output schema, the description covers purpose, side effect, and the drafting alternative. It could have noted what comes back on success (e.g., a message id) since no output schema exists, but the essential call-time information is present.

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%, including formats for recipients, bodyFormat enum values, and attachment source alternatives, so the schema carries the parameter burden. The description adds no parameter-level meaning beyond it, which is the baseline-3 case.

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 pair and resource ('compose and immediately send a new email') plus the visible side effect (a copy is saved in Sent Items). An agent can tell this apart from create_draft without consulting any schema.

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

Usage Guidelines5/5

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

Gives an explicit routing rule with a condition: use create_draft instead if the user wants to review first. That is a concrete when-to-use-this vs when-to-use-alternative decision, not an implied one.

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