OffshoreProz Agent Company

recommend_structure

FREE, no API key. Recommend the optimal structure for an autonomous AI agent business: the US$299 Wyoming LLC (the fast, bank-friendly wedge — most agents start here), the Nevis LLC "Agent Company" (asset-protection fortress + 0% tax on non-Nevis income), or Nevis + a wholly-owned Wyoming USD subsidiary when the agent needs fiat rails (Stripe, US banking). Also flags a Delaware C-corp holding if the founder will raise equity. Advisory only, nothing stored — run agent_company_diagnostic first for the exposure score, then this for the structure, then create_standalone_company or create_formation_request to act.

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": {
      "agent_activity": "<agent_activity>"
    },
    "name": "recommend_structure"
  }
}

Input Schema

Name	Required	Description
`holds_assets`	No	Whether the agent holds significant treasury/assets (informational — the Nevis fortress already applies).
`agent_activity`	Yes	What the AI agent does — e.g. "autonomous market-making", "runs ad campaigns and collects commissions".
`needs_fiat_usd`	No	Does the agent need to receive USD/fiat or card payments (Stripe), or US banking? If true, a Wyoming subsidiary is recommended. Most crypto-only agents leave this false.
`monthly_revenue_usd`	No	Estimated monthly revenue in USD (informational).
`raising_equity_capital`	No	Will the founder raise venture/equity capital from investors? If true, a Delaware C-corp holding is flagged.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.1/5.0

Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden, and it does disclose key traits: "FREE, no API key" and "Advisory only, nothing stored," which tell the agent this is a safe, non-mutating call. What it omits is the response shape — whether the recommendation comes back as prose, an enum, or a ranked list — which matters for an advisory tool whose entire value is the returned verdict.

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?

Front-loaded and information-dense: the recommended structure leads, the options follow as a parallel triple, then the caveat and the workflow. It is somewhat overstuffed with promotional framing ("bank-friendly wedge," "asset-protection fortress") that lengthens parsing without adding decision-relevant 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 5-parameter, single-required-field advisory tool this covers purpose, sequencing, side-effect profile, and the decision logic for each input flag. The remaining gap is that with no output schema, the description never says what the recommendation actually looks like when returned.

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 coverage is 100% and the property descriptions already spell out the consequence of each flag (needs_fiat_usd → Wyoming subsidiary, raising_equity_capital → Delaware C-corp, holds_assets → Nevis fortress). The body text largely restates those same mappings, adding only light framing ("most agents start here"), so 3 is the right baseline.

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?

Specific verb plus resource: "Recommend the optimal structure for an autonomous AI agent business," immediately enumerated into three concrete outcomes (Wyoming LLC, Nevis LLC, Nevis + Wyoming USD subsidiary) plus a Delaware flag. It is clearly distinct from agent_company_diagnostic (scoring) and the create_* siblings (execution).

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?

Gives an explicit ordered workflow: run agent_company_diagnostic first for exposure, then this for structure, then create_standalone_company or create_formation_request to act. Both the when and the named alternatives are stated, leaving nothing to inference.

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

All OffshoreProz Agent Company 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.