Skip to main content
Glama

Manage outreach

manage_outreach
Destructive

Draft and manage outreach messages to people at companies: accept the terms, draft, edit, redraft, discard, record the outcome and close a thread; build Mailbox campaigns, choose their message, edit or remove their emails and cancel them. Sending is send_email send_outreach or send_campaign. Actions: accept_terms, draft, edit, discard, regenerate, resolve, close_thread, create_campaign, choose_campaign_template, retry_campaign_templates, write_campaign_emails, edit_campaign_email, cancel_campaign. Call with action "help" for each action's fields.

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": {
      "action": "<action>"
    },
    "name": "manage_outreach"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
paramsNoFields for the action. Call with action "help" to list each action's fields.
target_idNoOne campaign email's id from get_outreach campaign or campaign_targets (targets[].id).
campaign_idNoA campaign's id from get_outreach campaigns (campaigns[].id).
outreach_idNoAn outreach message or thread id from get_outreach.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "accept_terms",
      -  "draft",
      -  "edit",
      -  "discard",
      -  "regenerate",
      -  "resolve",
      -  "close_thread",
      -  "help"
      -]New value: +[
      +  "accept_terms",
      +  "draft",
      +  "edit",
      +  "discard",
      +  "regenerate",
      +  "resolve",
      +  "close_thread",
      +  "create_campaign",
      +  "choose_campaign_template",
      +  "retry_campaign_templates",
      +  "write_campaign_emails",
      +  "edit_campaign_email",
      +  "cancel_campaign",
      +  "help"
      +]
    • addedInput schema / properties / campaign_id
      Added value: +{
      +  "description": "A campaign's id from get_outreach campaigns (campaigns[].id).",
      +  "pattern": "^[a-f0-9]{32}$",
      +  "type": "string"
      +}
    • addedInput schema / properties / target_id
      Added value: +{
      +  "description": "One campaign email's id from get_outreach campaign or campaign_targets (targets[].id).",
      +  "pattern": "^[a-f0-9]{32}$",
      +  "type": "string"
      +}
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: no email is sent by this tool, and it mutates existing thread and campaign state (discard, cancel_campaign, close_thread). It stops short of saying what state is lost on discard or whether edits are reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Usage and sibling routing are correctly front-loaded, but the sentence runs long with stacked semicolons, and the 13-value action list is reproduced verbatim from the schema enum, as is the "help" instruction already present in the params description. That duplicated content costs space without adding meaning.

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?

For a 13-action multiplexer with a free-form nested params object and no output schema, the description does the right things: scopes the domain, defers field detail to action "help", and blocks the mistaken assumption that it sends mail. It is thin on which actions are safe vs irreversible, but annotations plus the two-stage help pattern make it callable without guesswork.

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 80%, and the id parameters already document their provenance (get_outreach campaigns/targets[].id), so the schema carries the load and baseline 3 applies. The description adds only the pointer that per-action fields live behind action "help", which is essentially a restatement of the params field description.

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 names the resource (outreach messages to people at companies and Mailbox campaigns) and enumerates the concrete operations covered (accept_terms, draft, edit, discard, regenerate, resolve, close_thread, campaign create/choose/write/edit/cancel). It explicitly excludes sending, routing that to send_email, send_outreach, and send_campaign, so an agent can separate this tool from its siblings 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?

It states the boundary condition explicitly: this tool drafts and manages, while sending goes to send_email/send_outreach/send_campaign. It also tells the agent how to discover per-action requirements via action "help", which is the only practical guidance for a 13-action multiplexer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.