SalesBlink Cold Email

Create Sequence

create_sequence

Create a Sequence - Create a new email sequence/campaign. Recipients must be the account holder's own contactable audience (e.g. their own opt-in or otherwise consented contacts) — never addresses assembled by the model — and suppression/blocklist is always enforced. Sequences are created paused by default; launching (resuming) sends emails to recipients and must only happen after explicit user confirmation.

Input Schema

Name	Required	Description
`bcc`	No	BCC email address for all outgoing emails
`name`	Yes	Name of the sequence
`lists`	Yes	Array of list UUIDs to include in the sequence
`steps`	Yes	Sequence steps. Required and non-empty. Each email step must be {type: 'email', template_id: 'public-template-uuid'} with optional send_as: 'new' \| 'followup' (followup replies in the existing thread; ignored on the first email step, which always starts a new thread). Each delay step must be {type: 'delay', days: number}.
`folder`	No	Optional general folder ID to organize the sequence. Must be a folder created without a type (i.e., not an email-sender folder).
`paused`	No	Whether to create the sequence in paused state. Default true (the API pauses new sequences when omitted). When false, the sequence launches and starts sending emails (in ~5 mins with launchTimingMode 'now', or at scheduledAt when 'schedule') and requires confirm: true as the account holder's explicit approval.
`confirm`	No	Required when paused is false — confirms the account holder explicitly approved launching the sequence
`delayTo`	No	Maximum delay in minutes
`senders`	Yes	Comma-separated sender UUIDs
`starred`	No	Whether to star the sequence
`skip_esg`	No	Skip ESG detection
`timezone`	No	IANA timezone for scheduled sending, e.g. 'Asia/Calcutta' or 'America/New_York'. Required when launchTimingMode='schedule'; otherwise it defaults to America/New_York.
`autoPause`	No	Enable auto-pause
`delayFrom`	No	Minimum delay in minutes
`evergreen`	No	Enable evergreen sequence
`plainText`	No	Send as plain text email
`auto_reply`	No	Enable auto-reply detection
`riskyEmail`	No	Send to contacts with risky email status
`validEmail`	No	Send to contacts with valid email status
`bouncePause`	No	Pause on bounce threshold reached
`scheduledAt`	No	Launch time. UTC milliseconds OR an ISO 8601 datetime with timezone offset, e.g. '2026-07-08T16:30:00+05:30' for 4:30 PM IST. Required when launchTimingMode='schedule'.
`delayEnabled`	No	Enable sending delay between emails
`invalidEmail`	No	Send to contacts with invalid email status
`workspace_id`	No	Workspace ID this action applies to. When omitted, the current or default workspace is used.
`matchProvider`	No	Match email provider when sending
`autoTagReplies`	No	Auto-tag replies
`checkEmailOpen`	No	Check if recipient opened previous email
`bounceThreshold`	No	Bounce threshold before pausing
`checkEmailClick`	No	Check if recipient clicked a link in previous email
`checkEmailReply`	No	Check if recipient replied to previous email
`launchTimingMode`	No	When to launch: 'now' (default, starts in ~5 mins) or 'schedule'
`emailSendingHours`	No	Custom email sending hours for each day of the week (Monday-Sunday). Default: weekdays 09:00-17:00 enabled, weekends disabled.
`stopWhenReplyRecieved`	No	Stop sequence when recipient replies
`checkEmailBeforeSending`	No	Verify email before sending. When enabled user must approve email before they can be sent
`sendToOnlyVerifiedEmail`	No	Only send to verified emails
`stopWhenReplyRecievedWhen`	No	When to stop sequence on reply: 'contact' = stop for this contact only, 'contact-with-same-domain' = stop for all contacts sharing the same domain

Output Schema

Name	Required	Description	Default
`result`	No	The raw result returned by the SalesBlink tool.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 24, 2026

TDQS

A4.1/5.0

Behavior5/5

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

The annotations only say the tool is a non-destructive write with open-world effects. The description adds policy context they do not cover: recipients must come from the account holder's own consented audience and must never be addresses the model assembled, suppression and blocklist are always enforced, and sequences are created paused by default. It also spells out the consequence of launching, which is that emails get sent.

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?

Three sentences, front-loaded with the purpose and then with the highest-risk constraints. The only waste is the redundant 'Create a Sequence -' prefix that restates the title.

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?

Given 36 parameters, 100% schema coverage, and an output schema, the description carries only the non-schema-recoverable policies, which it does well. Minor gap: it does not tie recipients to the required `lists` UUID parameter, so the agent must connect the consent rule to that field on its own.

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 every one of the 36 parameters, including launchTimingMode, confirm, and send_as nesting, is already documented inline. The description adds only the paused-by-default behavior, without extra argument formats. That baseline 3 is appropriate when the schema carries the parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a specific verb and resource: 'Create a new email sequence/campaign.' That clearly separates it from read/update siblings, but the family of adjacent write tools (clone_sequence, update_sequence, update_sequence_status) is not named, so differentiation has to be inferred from the verbs alone.

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 gives an explicit precondition for the risky path: launching may happen only after explicit user confirmation. However, it never says when to prefer clone_sequence over create_sequence, or when to use update_sequence on an existing sequence instead. Usage is clear within the call, but not relative to alternatives.

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

All SalesBlink Cold Email tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.