Conecto

Save an outreach campaign

outreach_save_campaign

Create an outreach campaign, or change one (pass campaign_id): its name, the mailboxes it sends from (they share the load, each within its own daily limit), the emails (a first email and up to four follow-ups, each with delay_days), the audience, a first line for each person, the sending days and hours in a time zone, and its own daily limit. The audience is one of: a prospect search's people with a working email (prospect_search_id), a CRM segment, or everyone with a tag; people who unsubscribed, bounced, said no, replied before or are in another campaign are left out, and the reply says who. You write every email; Conecto writes nothing. Placeholders: {first_name} (the person's first name), {name} (the person's full name), {company} (their company), {first_line} (the first line you wrote for them in first_lines), {sender_name} (the name of the mailbox that sends it), {sender_first_name} (that name's first word). Every step passes Conecto's writing check before a campaign can start, and a refusal names each fix: no em dashes; no stock openers ("I hope this email finds you well", "I'm reaching out") or closers ("Best regards", "Looking forward to hearing from you"); no "not X, but Y" contrasts or slogans; no hype or filler words ("seamless", "game-changer", "I'd love to"); at most 120 words an email and 60 characters a subject; one link and one ask at most; no "Re:" on a first email; no unsubscribe line of your own (Conecto adds one); and every placeholder filled for every person. The reply has the writing check's fixes; show the person outreach_preview, then start it with outreach_start. While it is a draft everything can change; once it started, only its name, mailboxes, schedule and daily limit, while it is paused. Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "outreach_save_campaign"
  }
}

Input Schema

Name	Required	Description
`name`	No
`steps`	No
`audience`	No	One of tag, segment or prospect_search_id.
`schedule`	No	When emails go: Monday to Friday, 9 to 17, in the account's time zone unless given.
`campaign_id`	No	The campaign_id outreach_save_campaign answered with.
`daily_limit`	No	Emails a day for this campaign; its mailboxes' own limits still hold.
`first_lines`	No	A first line you wrote for each person, by their email: {first_line} in an email.
`mailbox_ids`	No	Mailboxes from outreach_mailboxes, in the order they take turns.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only say non-read-only, non-destructive, non-idempotent, closed-world; the description adds far more: the writing check and its full rule list, the audience exclusions (unsubscribed, bounced, declined, replied, in another campaign), that the reply names those people, the draft-vs-started editability lifecycle, and the cost ('Free'). That is genuine behavioral context an agent cannot get from the structured fields.

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?

Front-loaded with the core purpose and workflow before the rule detail, and almost every sentence carries unique information. It loses a point for being one undifferentiated block paragraph with several very long compound sentences (the writing-check list in particular) that would read far better as structured bullets.

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 complex 8-parameter nested write tool with no output schema, the definition covers creation, update scope, audience resolution, message composition constraints, the pre-flight validation failure mode, and the next tools to call. An agent has enough to invoke it correctly on the first attempt.

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?

At 75% schema coverage, the description carries real weight: it explains that mailboxes share the load within per-mailbox daily limits, that steps are one first email plus up to four follow-ups with delay_days, that audience is exactly one of prospect_search_id / segment / tag, and that first_lines is keyed by person. It also enumerates the supported placeholders, which appear nowhere in 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 specific verb+resource pair ('Create an outreach campaign, or change one (pass campaign_id)') and immediately enumerates the editable surface (name, mailboxes, emails, audience, first lines, schedule, daily limit). This clearly separates it from outreach_preview, outreach_start, outreach_pause, and outreach_campaigns.

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 states the create-vs-update branch via campaign_id, and prescribes the workflow: 'show the person outreach_preview, then start it with outreach_start.' It also gives the when-not condition for mutation ('once it started, only its name, mailboxes, schedule and daily limit, while it is paused').

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

All Conecto 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.

Resources

Need Help?