freedom-mcp

Create ICP

create_icp

Destructive

Create a NEW Ideal Customer Profile (ICP) from scratch and save it — no Customer Hunter UI needed. Use this when get_icps returns hasICPs:false (the company has none yet) or to add another target customer profile. To CHANGE an existing ICP, use update_icp instead.

Routing: Consult get_product_context + get_setup_state (get_company too if they have a site) before authoring — don't invent an audience; a duplicate name fails, use update_icp instead

[write-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time. Call it on the first clear ask; the card is the yes — do not re-ask in chat.]

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Persona name. Required. Used to derive the ICP id/filename. INTERNAL targeting label (may be an evocative codename) — never published.
`class`	No	'customer' (default) or 'partner' — partner = a distribution/affiliate ICP, not an end-buyer.
`title`	No	One-line descriptor of the persona.
`channels`	No	Where they spend attention (communities, publications, events).
`companyId`	Yes	FreedomOS company id to act within (you must be a member). Required for company-scoped tools.
`painThemes`	No	Recurring pain themes.
`publicName`	No	The public-facing audience label to use in published copy — NEVER the internal persona name/codename. Plural noun phrase, e.g. "compounding pharmacy owners". Optional — auto-generated from the persona when omitted.
`agentProfile`	No	How this customer's own AI agent participates in buying: { tier: 'ambient' \| 'assisted' \| 'delegated' \| 'builder', agents: string[], surfacesRead: string[], purchasePath: string, autonomyNotes: string }. tier is required and must be one of the four values.
`demographics`	No	role, companySize, industry, techStack[].
`dreamOutcome`	No	The outcome they dream of.
`techSavviness`	No	Tech comfort level.
`financialProfile`	No	revenueRange, typicalDealSize, budgetAuthority, buyingBehavior, growthStage, priceSensitivity.
`nightmareScenario`	No	The 3am problem / nightmare scenario.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 23, 2026

changedInput schema / properties / channels / description

Previous value: -"Where they spend attention."New value: +"Where they spend attention (communities, publications, events)."

Changed2 schema fields changedJul 23, 2026

addedInput schema / properties / agentProfile

Added value: +{
+  "description": "How this customer's own AI agent participates in buying: { tier: 'ambient' | 'assisted' | 'delegated' | 'builder', agents: string[], surfacesRead: string[], purchasePath: string, autonomyNotes: string }. tier is required and must be one of the four values.",
+  "type": "object"
+}

addedInput schema / properties / class

Added value: +{
+  "description": "'customer' (default) or 'partner' — partner = a distribution/affiliate ICP, not an end-buyer.",
+  "enum": [
+    "customer",
+    "partner"
+  ],
+  "type": "string"
+}

First observedJul 19, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations indicate destructiveHint=true, which aligns with the creation action. The description goes beyond annotations by disclosing the write-tier approval requirement, which is a critical behavioral trait not covered by annotations. It also clarifies that the approval card is the yes and not to re-ask, adding useful interaction guidance.

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?

The description is moderately long but front-loaded with the primary purpose and usage conditions. The routing guidance and approval note are relevant but add length. Slightly overwritten yet still efficient.

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 complex tool with 13 parameters and nested objects, the description covers the creation context, routing, failure mode, and approval flow. The schema covers parameters, and no output schema is present, so the description's focus on inputs and process is appropriate. It is complete for an agent to call correctly.

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 description coverage is 100%, so the schema already documents parameters well. The description adds value by explaining the 'name' parameter is an internal targeting label and that publicName should be used for published copy, reinforcing the distinction. It also clarifies the 'class' parameter effectively.

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 clearly states the action (Create a NEW Ideal Customer Profile), the resource (ICP), and the condition for use (when get_icps returns hasICPs:false or to add another). It also differentiates from update_icp explicitly, providing strong sibling distinction.

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?

Explicitly provides when to use (create when none exist or add another), when not to use (to change existing use update_icp), and prerequisites (consult get_product_context + get_setup_state before authoring). It also warns about duplicate names and to use update_icp instead.

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

All freedom-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.

Resources

Need Help?