Argorant

Choose the mailboxes that send

argorant_set_campaign_senders

Add sending mailboxes to a campaign, chosen by domain, tag, status, address or all_connected=true. Use it to give a campaign its mailboxes before a launch. To take one off use argorant_remove_campaign_sender, to see them use argorant_list_campaign_senders, and to find the domains, tags and statuses there are use argorant_list_inboxes. Domains and tags take mailboxes that are ready to send (sendable) unless you give status, such as ["sendable", "warming"] to also add new mailboxes, which start sending after their first 24 hours, or ["any"]. Mailboxes always come from the campaign's own workspace. With preview=true nothing changes and the answer counts what would be added, by domain and status; do that first for a large choice and tell the user the number. Mailboxes already on the campaign stay, so calling twice adds nothing twice. Nothing is sent. More in the docs at https://docs.argorant.com/docs/agents/tools#campaigns

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": "argorant_set_campaign_senders"
  }
}

Input Schema

Name	Required	Description
`tags`	No	Mailboxes that carry all of these tags.
`emails`	No	Addresses, when only a few. For many, use domains or tags.
`status`	No	sendable (default for domains and tags), warming, not_connected, needs_attention, paused, or any.
`domains`	No	Every mailbox on these domains, such as acmemail.com.
`preview`	No	Set it to true to only count what would be added and change nothing.
`campaign_id`	Yes	The campaign's id, from argorant_list_campaigns.
`all_connected`	No	true takes every signed-in mailbox of the workspace.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the behavior that matters: preview=true changes nothing and returns counts split by domain and status, already-attached mailboxes are left in place so repeat calls are additive-noop, mailboxes are always scoped to the campaign's own workspace, and "Nothing is sent." These are exactly the traits an agent needs before mutating a campaign.

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 purpose, then alternatives, then the status-default rule and preview guidance; almost every sentence carries distinct information. It is a single dense paragraph, and the status/preview rules would scan better as separate clauses or bullets, but there is little wasted wording.

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 7-parameter mutation tool with an output schema, the description covers the remaining gaps: workspace scoping, idempotency, preview semantics including what the counts break down by, and the effect of status on the default sendable filter. Return shape is handled by the output schema, so nothing an agent needs to call this safely is missing.

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

Parameters4/5

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 real semantics beyond the field docs: domains and tags implicitly filter to sendable unless status is given, passing ["sendable","warming"] pulls in new mailboxes that start sending after their first 24 hours, and ["any"] disables the filter. That interaction between parameters is not derivable 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?

The description opens with a specific verb and resource ("Add sending mailboxes to a campaign") and then enumerates the selection axes: domain, tag, status, address or all_connected=true. It names the exact sibling tools it replaces or complements (argorant_remove_campaign_sender, argorant_list_campaign_senders), so an agent can distinguish it without opening any 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?

Usage is fully routed: run it before a launch, use argorant_remove_campaign_sender to take one off, argorant_list_campaign_senders to see them, and argorant_list_inboxes to discover the domains/tags/statuses to feed in. It also gives an explicit sequencing rule — do preview=true first for a large selection and report the count to the user.

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

All Argorant 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.