Skip to main content
Glama

Send an email from my domain

email_send
Destructive

Use this when the member asks to send or email someone from their own business domain (Connections Send). Sends ONE real message, now or at a scheduled time; it lands in the recipient's inbox and cannot be recalled, and dry_run:true returns the exact message without sending it. The sender must be on a domain this workspace has connected and verified. When nothing goes out, the reply is an error naming why: a suppressed recipient, an unverified domain, a spent daily ceiling, or no credits. email_sent reads what went out and what happened to each message; email_drafts saves one to finish later.

Input Schema

NameRequiredDescriptionDefault
ccNoOptional carbon-copy recipients.
toYesOne recipient address, or several.
bccNoOptional blind-copy recipients.
fromYesThe sender, on a domain this workspace has connected and verified. May be 'Name <you@yours.com>'.
htmlNoThe HTML body. Not with `template`.
textNoThe plain-text body. Send text, html, or both. Not with `template`.
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
dry_runNotrue previews the exact call with nothing sent.
projectNoWorkspace to run this call in (id or name).
subjectNoThe subject line. Required unless `template` names a stored template that carries one.
audienceNoDoes this person already know the sender? warm = they know you or asked for this mail; cold = no prior relationship. Required for every recipient, no default: a send with no audience returns an error. One value covers the whole message; recipient_audience sets it per address and wins.
reply_toNoWhere replies should go, when that is not the sender.
templateNoThe name of a template stored in this workspace (e.g. 'order-receipt'), used INSTEAD of text/html. Its placeholder values go in `variables`.
variablesNoValues for the template's {{placeholders}}, as a flat object. Every placeholder needs one.
referencesNoThe thread's earlier Message-IDs, oldest first (the References header of the message being answered). Only read with in_reply_to, which is appended when missing.
in_reply_toNoWhen this answers an email someone sent (a vendor's support ticket, say): that message's Message-ID, e.g. '<abc@zendesk.com>'. The reply then joins their existing thread; without it, their system opens a new one.
scheduled_atNoOptional send time: an ISO instant WITH a timezone ('2026-10-01T09:00:00Z') or a relative time ('in 2 hours'). A time with no timezone returns an error asking for the zone. Omit to send now.
idempotency_keyNoYour own key for this message. Sending the same key twice returns the first result instead of sending again - set it whenever a retry is possible.
recipient_audienceNoThe audience per address, as a flat object whose values are 'warm' or 'cold': { 'person@yours.com': 'warm' }. Wins over audience for the addresses it names.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

The description adds substantial context beyond the annotations: the message lands in the recipient's inbox, cannot be recalled, and `dry_run:true` returns the exact message without sending. It also discloses prerequisites (verified sender domain) and the exact error conditions a failed send may return, such as suppression, unverified domain, daily ceiling, or no credits.

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 front-loaded with the core usage condition and safety fact. It is dense but every sentence earns its place: usage, irreversibility, dry-run behavior, prerequisites, error outcomes, and sibling routing are all covered without filler.

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

Completeness5/5

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

For a 19-parameter, nested mutation tool with no output schema, the description covers the critical missing context: irreversibility, dry-run preview, verified-domain requirement, and error conditions. Parameter details are fully documented in the schema, so the description does not need to repeat 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 input schema already documents every parameter thoroughly. The description adds some useful meaning around `dry_run` and sender-domain verification, but most parameter semantics are carried by the schema. A baseline 3 is appropriate when the schema does the heavy lifting.

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 and resource: sending one real email from the member's business domain. It clearly distinguishes this from `email_drafts` (saving to finish later) and `email_sent` (reading what went out). An agent can identify both the action and its scope without inspecting siblings.

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?

It explicitly states when to use this tool: when the member asks to send or email someone. It names the alternatives and their roles: `email_sent` reads outcomes, `email_drafts` saves for later. It also clarifies that `dry_run:true` previews without sending and that scheduled sends are supported.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources