Arc & Ledger Tax Tools

Estimate IRS penalties and interest

estimate_irs_penalty

Read-only

Use this when someone owes the IRS and asks how much the penalties and interest will be, or what late filing/paying costs. Estimates the failure-to-file (5%/mo) and failure-to-pay (0.5%/mo) penalties and interest on a balance, and explains the current Automatic Exemption from Penalty, First Time Abate, and reasonable-cause relief paths.

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": {
      "balance_owed_usd": "<balance_owed_usd>",
      "months_late": "<months_late>"
    },
    "name": "estimate_irs_penalty"
  }
}

Input Schema

Name	Required	Description
`months_late`	Yes	Whole months past the deadline. The failure-to-file penalty counts any part of a month as a full month.
`return_filed`	No	Whether you actually FILED the return (even if you did not pay). If false, the larger 5%/month failure-to-file penalty applies. Defaults to false (not filed).
`balance_owed_usd`	Yes	The unpaid tax balance (the tax itself, before penalties and interest).

Output Schema

Name	Required	Description
`relay`	Yes	Instruction to the calling assistant: relay figures and dates verbatim (identical on every response).
`next_step`	Yes	A single review link appropriate to this server surface.
`disclaimer`	Yes	General-information disclaimer (identical on every response).
`source_url`	Yes	The arcandledger.com page that backs this answer.
`server_version`	No	Server release that produced this response (matches GET /version).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 26, 2026

changedOutput schema / properties / next_step / description

Previous value: -"A single human handoff to the firm."New value: +"A single review link appropriate to this server surface."

Changed2 schema fields changedJul 13, 2026

addedOutput schema / properties / relay

Added value: +{
+  "description": "Instruction to the calling assistant: relay figures and dates verbatim (identical on every response).",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "disclaimer",
-  "source_url",
-  "next_step"
-]New value: +[
+  "disclaimer",
+  "relay",
+  "source_url",
+  "next_step"
+]

Changed1 schema field changedJul 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "disclaimer": {
+      "description": "General-information disclaimer (identical on every response).",
+      "type": "string"
+    },
+    "next_step": {
+      "description": "A single human handoff to the firm.",
+      "properties": {
+        "label": {
+          "type": "string"
+        },
+        "url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "label",
+        "url"
+      ],
+      "type": "object"
+    },
+    "server_version": {
+      "description": "Server release that produced this response (matches GET /version).",
+      "type": "string"
+    },
+    "source_url": {
+      "description": "The arcandledger.com page that backs this answer.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "disclaimer",
+    "source_url",
+    "next_step"
+  ],
+  "type": "object"
+}

First observedJul 8, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, which align with the description's estimation nature. The description adds context about specific penalties and relief paths without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with usage guidance, followed by a precise list of what the tool estimates. No extraneous words.

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?

Given the tool's simplicity (3 params, has output schema, no nested objects), the description covers when to use, what it estimates, and relief paths. No gaps identified.

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?

Input schema has 100% description coverage, so each parameter is already documented. The description does not add new parameter-level details beyond the schema, meeting the baseline expectation.

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 specifies the verb 'estimate' and the resource 'IRS penalties and interest', and distinguishes from sibling tools like check_resolution_options and decode_irs_notice by focusing on penalty/interest estimation and relief paths.

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?

The description explicitly states when to use this tool ('when someone owes the IRS and asks how much the penalties and interest will be') and implies the context (late filing/paying costs). It lacks explicit exclusions or alternatives but provides sufficient context.

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

All Arc & Ledger Tax Tools 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.