Skip to main content
Glama
mailkite

MailKite

Official

mailkite_send_event

Record application-level events like payment.failed to trigger automation sequences. Identify users by email or contactId, and use dedupeKey for idempotent retries without duplicate enrollments.

Instructions

Record one application-level fact about a user — user.created, trial.expiring, payment.failed. THE primary way a sequence starts on a developer platform: your application already knows when a payment failed, so it says so, and every enabled trigger listening for that name enrolls the contact with the payload as its input. Identify the subject with email or contactId (never both). Pass a dedupeKey to make retries idempotent: a repeat returns the original event with duplicate: true rather than enrolling anyone twice. Requires an API key (mk_live_…).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesEvent name: 1-64 characters of letters, digits, dot, dash, or underscore, starting alphanumeric. Names beginning `mailkite.`, `mailkite:`, or `email.` are reserved for platform events.
emailNoThe address this event is about. Give either this or `contactId`, never both. An address we don't hold a contact for still records — the event is an observation, not a subscription, so no contact is created as a side effect.
eventNoAlias for `name`, accepted so a payload written for another provider works unchanged. `name` wins when both are given.
payloadNoFree-form context carried with the event. Sequence steps read it as {{event.*}} for merge tags and, from conditions on, for branching.
contactIdNoA contact you own (ctc_…), as an alternative to `email`. Give either this or `email`, never both.
dedupeKeyNoIdempotency key. A second POST with the same key returns the ORIGINAL event and `duplicate: true` instead of recording a second one — so a retried webhook can never enroll the same contact twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.20.0

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important behaviors: retries with dedupeKey return the original event with duplicate:true, unknown addresses are recorded without creating a contact, name/event alias handling, reserved name prefixes, and an API key requirement. This significantly exceeds what readOnly/idempotent/destructive hints convey.

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 dense but not bloated: it front-loads the core action and examples, then covers subject identification, idempotency, and auth, all in a few sentences. The length is justified by the complexity of the tool.

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 six-parameter event-ingestion tool with no output schema, the description covers identification semantics, trigger enrollment, idempotent retries, reserved names, and auth. It could detail the success response shape or error conditions, but enough is present for an agent to call the tool correctly.

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 schema already documents every parameter. The description adds the mutual-exclusion rule (email/contactId never both) and the idempotency effect of dedupeKey, but most of this is also present in the parameter descriptions, so the incremental value is modest.

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 names a specific verb (record), a specific resource (application-level event), and concrete examples (user.created, trial.expiring, payment.failed), making the tool's job unmistakable. It also positions it as the primary way a sequence starts, which separates it from send/send_batch and from list_events.

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?

It clearly states when to use this tool: when the application already knows a fact like a failed payment and needs the event observed by every enabled trigger. It stops short of explicitly naming sibling alternatives such as list_events or create_trigger and saying 'use those instead,' but the context is otherwise clear.

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

Install Server

Other Tools