Skip to main content
Glama
mailkite

MailKite

Official
by mailkite
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
JavaScript
Hybrid

mailkite_start_sequence

Start a sequence for a contact by name or ID without a lookup, returning the enrollment to inspect, follow, or cancel. Responds with 409 and the reason when the contact is suppressed, already enrolled, or missing required input.

Instructions

Start a sequence for one contact, directly — when your code already knows WHICH sequence it wants. Takes a sequence NAME or id, so "start the dunning sequence" needs no lookup. Returns the enrollment it created: the run you then inspect, follow, or cancel. Refused with 409 when the address is suppressed, is already running on a reentry: "once" sequence, or is missing a required input — and the response says which. Reach for sendEvent instead when your code only knows what HAPPENED and policy should decide what reacts. Requires an API key (mk_live_…).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fromNoSender for this enrollment, when the sequence has no default (a send-triggered sequence normally inherits one from the triggering message, which a manual enroll does not have).
emailNoThe address to enroll. Give this or `contactId`.
inputNoThe sequence's input, checked against its declared signature. A missing required field refuses the start and says which — you find out here rather than days later as a blank merge tag.
sequenceYesPath parameter `sequence`.
cancelKeyNoYour own key for this enrollment. Cancel later with POST /v1/enrollments/cancel and this key — no need to store our id.
contactIdNoA contact you own (ctc_…), as an alternative to `email`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.20.0

TDQS

A5/5.0
Behavior5/5

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

Annotations are minimal (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description carries the burden of behavioral disclosure. It reveals error conditions (409 for suppression, already-running on 'once' sequences, missing input), the return value (the enrollment/run), the API key requirement, and the distinction from sendEvent — all beyond what annotations provide.

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?

Every sentence earns its place: the lead states the core purpose and the key differentiator, followed by concrete error semantics, the return value, the alternative tool, and the auth requirement. No redundancy; the most decision-relevant info is front-loaded.

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 tool with 6 parameters, a nested object (input), and no output schema, the description is thorough: it covers return value, error handling, auth, and the exact use-case versus a sibling. The schema's rich per-parameter descriptions complement the description, so nothing an agent needs to invoke it correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it clarifies that the sequence parameter accepts a name or id, explains the `from` parameter's fallback behavior, and details how `cancelKey` enables later cancellation without storing an id. These are genuinely useful clarifications an agent wouldn't get from the schema alone.

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?

Clearly states the action (start a sequence) and the target resource (a contact), with a specific qualifier ('when your code already knows WHICH sequence it wants'). It also names the exact sibling alternative (sendEvent) and the condition that selects it, so an agent can distinguish it without opening the 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?

Explicitly tells when to use this tool (when the sequence is known) and when not to (when policy should decide from an event, use sendEvent). It also explains the direct-by-name behavior ('start the dunning sequence needs no lookup'), which guides selection among the many sequence-related siblings.

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