mcp-server

Compare Formation Structures

compare_formation

Read-only

Side-by-side comparison of 2-6 formation structures across tax position, setup/annual costs, timeline, remote feasibility, substance requirements, banking tier, EU/FATF status, ideal client and not-for. Pass structures as an array of profile keys (e.g. ["us-llc-wy","ae-freezone","ee-ou"]). Comparative facts only — the right choice turns on the owner’s residence and goals; information, not advice.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`structures`	Yes	2-6 profile keys

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present only when the request could not be fulfilled.
`terms`	No	Acceptable-use and information-not-advice terms.
`source`	No	Attribution for the data, when it is not Mirabello Consultancy itself.
`book_url`	No	Link to request a consultation with a Mirabello specialist, for a personal case.
`provider`	No	Always "Mirabello Consultancy".
`disclaimer`	No	Information, not legal/tax/financial/immigration advice; figures indicative.
`data_updated`	No	Date the underlying dataset was last updated.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 8, 2026

removedOutput schema / properties / book_a_consultation

Removed value: -{
-  "description": "URL to book a Mirabello consultation.",
-  "type": "string"
-}

addedOutput schema / properties / book_url

Added value: +{
+  "description": "Link to request a consultation with a Mirabello specialist, for a personal case.",
+  "type": "string"
+}

changedOutput schema / properties / source / description

Previous value: -"Attribution for the data."New value: +"Attribution for the data, when it is not Mirabello Consultancy itself."

Changed1 schema field changedJul 27, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Mirabello response envelope. Tool-specific fields vary; the provenance/disclaimer envelope is always present.",
+  "properties": {
+    "book_a_consultation": {
+      "description": "URL to book a Mirabello consultation.",
+      "type": "string"
+    },
+    "data_updated": {
+      "description": "Date the underlying dataset was last updated.",
+      "type": "string"
+    },
+    "disclaimer": {
+      "description": "Information, not legal/tax/financial/immigration advice; figures indicative.",
+      "type": "string"
+    },
+    "error": {
+      "description": "Present only when the request could not be fulfilled.",
+      "type": "string"
+    },
+    "provider": {
+      "description": "Always \"Mirabello Consultancy\".",
+      "type": "string"
+    },
+    "source": {
+      "description": "Attribution for the data.",
+      "type": "string"
+    },
+    "terms": {
+      "description": "Acceptable-use and information-not-advice terms.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedJul 25, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so safety is covered. The description adds the advisory framing ('comparative facts only — information, not advice'), which is useful expectation-setting, but discloses nothing about limits, key resolution failures, or partial-match behavior.

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 with what is compared, then the input format, then the disclaimer — a logical order. The dimension list is long but each entry carries distinct selection value; no filler sentences.

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?

An output schema exists, so return values need no description, and the description covers input shape, cardinality bounds, comparable dimensions, and the advisory caveat. What is missing is guidance on where valid profile keys come from (e.g. find_formation_jurisdictions), a genuine gap for a key-array input.

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 coverage is 100% and there is a single required parameter, so the baseline would be 3. The description earns an extra point by supplying concrete example keys ("us-llc-wy", "ae-freezone", "ee-ou") that convey the key naming convention, which the schema does not.

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?

States a specific verb (side-by-side comparison), resource (formation structures), and bounded scope (2-6), then enumerates the exact dimensions compared (tax position, costs, timeline, substance, banking tier, EU/FATF, ideal client). This clearly distinguishes it from siblings like compare_programmes and compare_treaty_position.

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?

It explains how to invoke the tool (pass an array of profile keys, with an example), but never states when to reach for this over compare_programmes or compare_scenarios, nor any prerequisite for obtaining valid profile keys. Usage is implied rather than specified.

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

All mcp-server 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.