Skip to main content
Glama
agentisend

agentisend

Send email

send_email

Send one email now or at a scheduled time to one or many To, CC and BCC recipients, with templates, attachments and idempotency keys. Returns a message id and status.

Instructions

Purpose: send one email now, or at a time you name. Takes one recipient or a list. Each To, CC and BCC recipient counts as one email. NOT for: checking whether a send would work (preflight_email), sending many different messages at once (send_batch), or asking a person first (request_approval). Returns: the message id and its status, immediately. Delivery happens after; get_email has the outcome. Refusals name the gate and the cure: validation_error lists the bad fields, domain_not_verified points at verify_domain, suppressed_recipient says the address asked not to be contacted, agent_unconfirmed means every recipient has to be the human until POST /agent/verify, and recipient_ramp names when the next new recipient is allowed. Addresses ending in @simulator.agentisend.com cost nothing, reach nobody, and work before any domain is verified. from onboarding@agentisend.com delivers real mail only to this account's member sign-in addresses, 20 per UTC day, with no cc, bcc, attachments, tracking, or extra headers. Sending twice is sending twice: pass an idempotency_key and a retry returns the first message id instead of a second email.

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>"
    },
    "name": "send_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCarbon-copy addresses — one string or a list.
toYesOne recipient address, or a list of up to 50. A bare string is fine.
bccNoBlind carbon-copy addresses — one string or a list.
fromNoSender address, e.g. "Acme <hello@acme.com>". Optional when template_id names a template with a default sender; one given here overrides it.
htmlNoHTML body. Provide html, text or template_id.
tagsNoYour own labels, returned on every event for this message.
textNoPlain-text body. Provide html, text or template_id.
headersNoExtra RFC 5322 headers.
subjectNoSubject line. Optional when template_id names a template that has one.
reply_toNoWhere replies should go, if not the from address.
timezoneNoTime zone for a scheduled_at phrase such as "tomorrow 9am". An ISO time ignores this. Example: America/Los_Angeles. Omitted phrases are read in UTC.
topic_idNoSubscription topic. Naming one screens every recipient against what they said about that topic and adds the one-click unsubscribe headers for it.
attachmentsNoFiles to attach (max 100). One with content_id is an inline image.
template_idNoThe id or the alias of a published template to send instead of an inline body. Its subject, from and reply_to are used unless you pass your own.
scheduled_atNoISO 8601 time to send at, or a phrase such as "tomorrow 9am". Future times wait; cancel or reschedule until then.
idempotency_keyNoYour own key for this action. Retrying with the same key returns the first result instead of doing it twice — send one whenever a retry could double the effect.
template_valuesNoValues for the template variables.

Output Schema

NameRequiredDescriptionDefault
idNoIdentifier.
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
statusNoThe message status.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds substantial context: refusal codes and their remedies (domain_not_verified -> verify_domain, suppressed_recipient, agent_unconfirmed, recipient_ramp), the sandbox @simulator.agentisend.com domain, the onboarding@agentisend.com limits (20 per UTC day, no cc/bcc/attachments/tracking/extra headers), and the idempotency_key retry semantics. This is more than the annotations cover, but it does not contradict them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The Purpose / NOT for / Returns framing front-loads the decision-relevant content before the refusal taxonomy and sandbox caveats. It is long and the refusal sentence is a dense run-on, but nearly every clause carries operational information an agent needs for a 17-parameter open-world tool.

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 17-parameter, open-world, nested-object tool with an output schema, the description covers the gaps that structured fields cannot: refusal recovery paths, sandbox vs. real-delivery behavior, quota limits, and retry semantics. Nothing an agent needs to call it correctly appears missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by adding meaning the schema does not carry, notably that each To/CC/BCC address counts as a separate email (a quota and ramp implication) and that an idempotency_key makes a retry return the first message id. It does not add syntax detail for scheduled_at, template_id, or topic_id beyond the schema.

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?

Opens with a concrete verb and resource: "send one email now, or at a time you name. Takes one recipient or a list." It immediately states the unit of work (each To/CC/BCC recipient counts as one email), which lets an agent distinguish it from send_batch 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 Guidelines5/5

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

An explicit "NOT for" block names three siblings and the condition that selects each: preflight_email for dry runs, send_batch for many different messages, request_approval when a human must confirm. It also points to get_email for the post-send outcome, so the routing decision is fully specified.

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