reference-data

compute_statutory_interest

Read-onlyIdempotent

PAID ($0.02). Simple statutory interest on a principal at the cited statutory-interest series rate: Actual/365 simple, principal × (rate/100) × (days/365). Pass days, or from and to as YYYY-MM-DD (from inclusive, to exclusive). If both are sent and disagree, the call is refused free. A series with no numeric rate after materialization (mechanism-only) is refused free — a non-answer is not sold. Not legal advice. Jurisdiction-specific compounding and day-count statutes are not applied. Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. Every AE series is free to try. Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.10 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

Input Schema

Name	Required	Description
`to`	No	Period end, YYYY-MM-DD, exclusive.
`days`	No	Day-count days. Omit when from and to are set. If both are sent and disagree, the answer is refused free (HTTP 400).
`from`	No	Period start, YYYY-MM-DD, inclusive. Pair with to. Day count is calendar days from inclusive to to exclusive (UTC dates).
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.10; that SKU is not an MCP tool).
`principal`	Yes	Principal in the country's own currency. Must be a finite number greater than 0.

Output Schema

Name	Required	Description
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`question`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 17, 2026

changedInput schema / properties / receipt / description

Previous value: -"Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool)."New value: +"Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.10; that SKU is not an MCP tool)."

removedOutput schema / properties / label_basis / properties / source_type / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / label_basis / properties / source_type / type
```
Added value: +[
+  "string",
+  "null"
+]
```
removedOutput schema / properties / label_basis / properties / verification_age_days / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
addedOutput schema / properties / label_basis / properties / verification_age_days / type
```
Added value: +[
+  "number",
+  "null"
+]
```

Changed3 schema fields changedOct 13, 2026

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedOct 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "description": "Simple statutory interest at the cited rate",
+  "properties": {
+    "basis": {},
+    "bind_series": {},
+    "country": {
+      "type": "string"
+    },
+    "disclaimer": {},
+    "error": {
+      "description": "Present on a free refusal or error; no charge"
+    },
+    "explanation": {},
+    "how_to_pay": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "http_endpoint": {
+      "type": "string"
+    },
+    "no_charge": {
+      "type": "boolean"
+    },
+    "payment_required": {
+      "description": "true when the call needs payment; how_to_pay explains x402 or card",
+      "type": "boolean"
+    },
+    "price_usd": {
+      "type": "number"
+    },
+    "provenance": {
+      "description": "Cited official sources behind the answer"
+    },
+    "question": {},
+    "receipt": {
+      "description": "Ed25519 answer receipt when receipt=true on a paid success"
+    },
+    "status": {
+      "description": "Answer status, e.g. computed or an honest no-answer status",
+      "type": "string"
+    },
+    "x_next_bind": {}
+  },
+  "type": "object"
+}

AddedSep 25, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only declare the safety profile (readOnly, idempotent, non-destructive). The description goes well beyond: price ($0.02), free-refusal semantics for disagreeing dates and mechanism-only series, the api_key vs x402 payment paths, and receipt behavior. This is exactly the extra context annotations cannot carry.

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

Conciseness3/5

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

The core formula is front-loaded, but the block is long and partly redundant — 'Not legal advice' appears twice and the receipt/certified-extract distinction is restated from the schema. Pricing, refusal, and payment details all compete in one dense paragraph.

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 paid, open-world computation with an output schema (return values need not be described), the description covers pricing, payment paths, refusal edge cases, receipt verification, and scope limits. Nothing an agent needs to invoke it correctly is missing.

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% so the baseline is 3, but the description adds the days-vs-from/to mutual-exclusion consequence (a free refusal rather than a wrong answer) and the meaning of the receipt flag. The api_key payment behavior is also explained beyond the terse schema string.

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 and resource (statutory interest on a principal at a series rate) and pins down the exact method (Actual/365 simple, principal × rate/100 × days/365). An agent can distinguish this from compute_income_tax, compute_vat, and other compute_* siblings without opening a schema.

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?

Clearly states how to invoke it — pass either days or from/to, with the conflict-refusal rule — and sets a scope boundary (jurisdiction-specific compounding and day-count statutes are not applied). It does not explicitly route the agent among siblings, but the mechanics and exclusions are well covered.

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

All reference-data 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?