HeyLead

Overview Schema Source Related Servers Discussions Admin

create_campaign

Destructive

Create a LinkedIn outreach campaign by describing your target audience. Finds matching prospects and saves a draft campaign for review, with nothing sent until you launch it.

Instructions

Create a LinkedIn outreach campaign from a natural language description.

Finds people on LinkedIn who match the description and saves a draft;
nothing is sent until campaign(action='launch'). Use it for sales
prospecting, recruiting and candidate sourcing, research and
user-interview recruitment, job-search networking, investor and partner
outreach, vendor scouting and event invitations.

Describe your ideal customers and HeyLead will find them on LinkedIn.
Supports lead generation, prospect discovery, SDR automation, cold outreach,
and targeted B2B sales campaigns with AI-powered ICP-based targeting.
On first campaign, project_brief is asked explicitly (what you are building,
go-live, volume, what a vendor must confirm) — a homepage alone is not enough.

Args:
    target_description: Who to target (e.g., "CTOs at fintech startups",
        "freelance UX designers in London", "yoga studio owners in California")
    campaign_name: Optional name for the campaign.
    icp_id: Optional ID of a saved ICP from generate_icp. If provided,
        uses the saved ICP's enriched LinkedIn codes for precise targeting
        instead of generating a new one.
    company_context: Optional. Your website URL or 1-2 sentences about your
        product/company. Copied into project_brief when project_brief is omitted.
    project_brief: Optional. Full project paste the model sees: what you are
        building, go-live, volume, what a vendor must confirm. Required before
        launch, resume, or auto-send.
    mode: Always autopilot. Copilot mode removed.
    company_url: Optional LinkedIn company URL for account-based targeting.
        Searches for employees at that specific company matching the ICP.
        Example: "https://www.linkedin.com/company/google"
    voice_mode: Voice memo mode for follow-ups and replies. "text_only"
        (default), "mixed" (alternates text and voice), "voice_only", or "ab_test".
    connections_only: "on" to create a DM-only campaign targeting existing
        LinkedIn connections. Skips invitations and warm-up — sends DMs
        directly to people you're already connected with. Use when user says
        "existing connections", "DM my network", "message my connections".
    exclude_connections: ON BY DEFAULT for a new campaign: nobody who was
        already a 1st-degree connection before this campaign started is
        reached — refused at enrolment and skipped at send time rather than
        DMed. People who accept this campaign's own invitation still get
        the opener. Pass "off" to include existing connections (or turn it
        off later in the campaign settings). Defaults off only for a
        connections_only campaign. Use "off" when the user says
        "include my existing connections"; the old "on" is still accepted
        for "don't message my existing connections", "cold only",
        "skip people I already know". Cannot be combined with
        connections_only, which is its exact inverse.
    campaign_type: Prompt family: "outbound" (default) or "job_search".
        job_search writes a job-search campaign: the invitation note and
        the first DM may name the recipient's company and the role, use
        one credible proof point at most and never list a CV. InMail is
        not routed by this switch. Pair with connections_only="on" to
        write to people the sender is already connected to.
    force: True to create the campaign even when the goal <-> ICP audit
        returns `mismatch` (the ICP holds no plausible buyer for the goal).
        Leave False; a `partial` verdict never blocks, it only warns.

Input Schema

TableJSON Schema

Name	Required	Default
`mode`	No	autopilot
`force`	No
`icp_id`	No
`voice_mode`	No	text_only
`company_url`	No
`campaign_name`	No
`campaign_type`	No
`project_brief`	No
`company_context`	No
`connections_only`	No
`target_description`	Yes
`exclude_connections`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.10.375Sep 18, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations carry only readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the description carries the behavioral burden — and it delivers: drafts are saved and nothing is sent until launch; exclude_connections is ON by default with refusal-at-enrolment semantics; force can bypass an ICP audit mismatch while partial verdicts only warn; mode is always autopilot. Nothing in the description contradicts the annotations; the disclosed mutation aligns with destructiveHint=true.

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?

Front-loading is strong: the first two sentences state the verb, resource, and the critical no-send safety fact. But the description pads with redundant material — 'Describe your ideal customers and HeyLead will find them on LinkedIn' is marketing filler that repeats the opener, and the capability list ('lead generation, prospect discovery, SDR automation…') substantially duplicates the earlier use-case enumeration. Not every sentence earns its place, though the sheer length is largely justified by a complex 12-parameter tool with zero schema coverage.

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 destructive, open-world, 12-parameter tool with 0% schema coverage, the description is remarkably complete: all parameters explained, safety behavior disclosed, prerequisites stated (project_brief required before launch), and the launch hand-off specified. The output schema covers return values, so nothing an agent needs to invoke this tool correctly is left to inference.

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?

Schema coverage is 0%, so the description must compensate fully — and it does: every one of the 12 parameters gets meaning beyond name/type/default, with examples (target_description), cross-tool references (icp_id from generate_icp), interaction constraints (exclude_connections cannot combine with connections_only), trigger phrases ('DM my network', 'cold only'), and default behavior (exclude_connections ON BY DEFAULT). This is exactly the compensation the 0% coverage baseline demands.

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 statement: 'Create a LinkedIn outreach campaign from a natural language description,' then immediately draws the boundary with 'saves a draft; nothing is sent until campaign(action="launch").' This cleanly separates it from send-type siblings like generate_and_send and send_message, and from the launch tool campaign, without needing to open 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides concrete use cases (sales prospecting, recruiting, research, networking, vendor scouting, event invitations) and explains the draft-then-launch workflow, pointing at campaign(action='launch') as the follow-up step and generate_icp as an input source. It never explicitly states when not to use it or names alternatives such as edit_campaign or engage_prospect, so the guidance is clear context without formal exclusions.

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