Add selected contacts (by ID) to an existing campaign. Blacklist of domains/companies, duplicate checks and manual exclusion are applied automatically. Campaign steps (visit → connect → message) are then scheduled per template and daily limits. Returns how many were added vs filtered.
| Name | Required | Description | Default |
|---|---|---|---|
| campaign_id | Yes | UUID of the campaign | |
| contact_ids | Yes | Array of contact UUIDs to add |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide idempotentHint=true and no destructive hint. The description adds behavioral details: automatic blacklist/duplicate/manual exclusion checks, scheduling of steps, and return of added vs. filtered counts. This goes beyond annotations, fully disclosing the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each serving a purpose: action, process, result. No wasted words. Front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description compensates by stating the return value (added vs. filtered). The tool is simple; the description covers all needed aspects for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds context that contacts are added by ID and that automatic filters apply, complementing the parameter descriptions. It does not repeat schema info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'Add selected contacts (by ID) to an existing campaign.' It uses a specific verb and resource, and distinguishes from sibling tools like 'create_campaign' or 'list_contacts' by focusing on adding to an existing campaign.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by describing automatic filtering (blacklist, duplicates, manual exclusion) and the scheduling of campaign steps. While it doesn't explicitly state when to use vs. alternatives, the context of sibling tools makes this less critical. It could benefit from an explicit 'when to use' statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but there is some overlap among search tools (search_job_postings, search_google_xray, search_linkedin_people, search_web) and messaging tools (send_connection_request, send_linkedin_message, reply_to_chat). However, detailed descriptions clarify the differences.
All tools follow a consistent verb_noun snake_case pattern (e.g., add_contacts_to_campaign, list_campaigns). No mixing of conventions.
48 tools is high but justifiable given the broad domain (LinkedIn outreach, CRM, campaigns, job postings, etc.). However, some tools could be consolidated (e.g., multiple search tools).
The tool set covers the entire workflow: searching, connecting, messaging, campaign management, CRM operations (fields, stages, tasks, notes), job postings, and posting. No obvious gaps.
