icp-intelligence-mcp

Lookalike Signal Generator

lookalike_signal_generator

Read-only

Helps you decide how to find more accounts like your best ones. You give your ICP's company profile, technologies, champion titles and buying triggers, and optionally what you sell and the platforms you use. You get targeting criteria and search queries for each platform, one signal for each trigger, and search keywords from what you sell and the sector. It writes criteria, not data: it finds no companies or contacts.

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": {
      "champion_titles": "<champion_titles>"
    },
    "name": "lookalike_signal_generator"
  }
}

Input Schema

Name	Required	Description
`company`	No	Optional: your company or product name, so the answer can name it
`platforms`	No	Optional: the sections to include (linkedin, google_ads, 6sense, zoominfo). Left out, every section is included
`buying_triggers`	No	Events that trigger buying
`champion_titles`	Yes	Job titles of your champions
`product_category`	No	Optional: what you sell (for example "spend management software"), used for search keywords and sector notes
`icp_firmographics`	No	Firmographic criteria
`icp_technographics`	No	Technologies your ICP typically uses

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 17, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With readOnlyHint, destructiveHint=false and openWorldHint=false already supplied, the annotations cover the safety profile. The description earns credit for the explicit negative capability ('finds no companies or contacts') and for enumerating the shape of the output, plus the default that omitting platforms includes every section. It does not mention permissions, limits, or how the upstream account data is sourced, so it lands at a solid rather than rich level.

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?

Three sentences, front-loaded with the purpose and ending on the most important constraint (no data returned). Almost every clause carries information, though the opening 'Helps you decide how to find' is slightly softer than a direct verb such as 'generates'.

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 seven-parameter tool with a nested object and no output schema, the description compensates well by describing the return values in prose (per-platform criteria and queries, per-trigger signals, keywords). Required versus optional input handling is covered, and the no-data caveat prevents the most likely misuse.

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 100% and every parameter, including the nested firmographics object, is documented in the schema itself. The description restates those inputs at a high level and adds a light output mapping (one signal per trigger, queries per platform), but introduces no syntax, format, or validation detail beyond the schema — so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete purpose: turn ICP inputs (firmographics, technographics, champion titles, triggers) into targeting criteria and per-platform search queries. The closing line 'It writes criteria, not data: it finds no companies or contacts' sharply delimits the output. It never names any of the sibling ICP tools, so an agent gets no explicit differentiation from icp_deep_dive or icp_scoring_model beyond the 'lookalike' framing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is conveyed through an input/output contract ('You give ... You get ...'), which implies when the tool fits, and 'optionally' flags which inputs can be omitted. There is no explicit when-not-to-use guidance and no named alternative when the agent wants an ICP audit or scoring versus lookalike signal generation.

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

All icp-intelligence-mcp 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.