Conecto

Start an outreach campaign

outreach_start

Start sending a campaign the person approved. Emails go within its days and hours, spread across the day and across its mailboxes, each mailbox within its daily limit; follow-ups thread under the first email and stop for anyone who replies; every email carries an unsubscribe line, and anyone who unsubscribes is never emailed again by any campaign. Each person costs $0.01 when their first email leaves, for their whole sequence and reply tracking; nobody who is never emailed costs anything. Refused until the writing check passes, with each fix named. Some countries, Germany among them, need a person's prior consent even for business email: the business answers for whom it writes to, so check with the person before you write to people there. Free.

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": {
      "campaign_id": "<campaign_id>"
    },
    "name": "outreach_start"
  }
}

Input Schema

Name	Required	Description	Default
`campaign_id`	Yes	The campaign_id outreach_save_campaign answered with.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only declare the CRUD-ish safety profile (not read-only, not destructive, not idempotent). The description goes far beyond that: send windows and day/hour spreading, mailbox rotation under daily limits, follow-up threading that stops on reply, mandatory unsubscribe lines with global suppression, per-person pricing ($0.01 on first send, free if never emailed), and a hard refusal gate. This is exactly the operational context annotations cannot carry.

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 action and the approval precondition, then layered with behavior, cost, and compliance. The semicolon-chained run-ons are dense, but nearly every clause carries decision-relevant information (cost, suppression, refusal, jurisdiction). Slightly tighter grouping would earn a 5.

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?

Very complete for a launch tool: preconditions, scheduling behavior, pricing, compliance, and failure mode are all covered despite having no output schema. The one gap is that it does not say what a successful call returns or how the agent should confirm delivery started.

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?

There is a single parameter with 100% schema description coverage that already explains campaign_id comes from outreach_save_campaign. The description adds no further detail about the identifier or its format, so the schema does all the work — baseline 3 applies.

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?

States a specific verb and resource ('Start sending a campaign') plus a hard precondition ('the person approved'), which distinguishes it from the pause/resume/stop/preview siblings without needing to name them. An agent can tell this launches delivery rather than modifying a campaign.

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?

Implies the preconditions clearly: the campaign must already be approved, and it is 'refused until the writing check passes.' It also flags the need to confirm prior consent for recipients in Germany and similar jurisdictions. It never explicitly names the sibling alternatives (outreach_preview, outreach_pause, outreach_stop), so it falls just short of the 5 bar.

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?