euroref — European government reference data

register_alert

Bind a webhook so the next gazette does not silently stale a value you already paid for. REGISTERING IS FREE. Register: $0 · Delivery after trial: $0.05. First 3 deliveries are free; later deliveries are $0.05 and refunded if the webhook fails to send. HMAC-SHA256 signed. Two watch types on the same call: • series: ["za/vat-registration-threshold", "ke/", ""] → series.changed when the served value or its effective date moves. On usaref those watches are statutory (minimum-wage, income-tax, statutory-interest, sales-tax, public-holidays), not a FRED-macro subscription. • sources: [""] → source.changed when the document BYTES change (old/new sha256 + citing series). Bytes ≠ value. Value changes arrive as series.changed. Unknown URLs refuse free (source_not_fingerprinted). Max 20 series + 20 sources. Required: url. Optional: api_key stored on the subscription to fund deliveries after the trial. This call does not meter that key. Prefer this over polling get_changes if you are a long-running agent. This is retention, not a new data product.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	Webhook endpoint that will receive HMAC-SHA256 signed events
`series`	No	Value watches, e.g. ["za/vat-registration-threshold", "ke/", ""]
`api_key`	No	Optional prepaid key stored on the subscription to fund deliveries after the trial. This call does not meter it.
`sources`	No	Exact official-source URLs from a series source.url. Unknown URLs are refused free.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present on a free refusal or error; no charge
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "description": "Alert subscription result (id, secret, trial) or refusal",
+  "properties": {
+    "bind_series": {},
+    "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"
+    },
+    "x_next_bind": {}
+  },
+  "type": "object"
+}

AddedSep 25, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Beyond the annotations (openWorld, non-idempotent, non-destructive), the description discloses cost structure ($0 register, $0.05 delivery after trial, first 3 free, refunded on send failure), HMAC-SHA256 signing, hard limits (20 series + 20 sources), and refusal behavior (source_not_fingerprinted for unknown URLs). This is exactly the extra behavioral context an agent needs and cannot get from the structured fields.

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 purpose is front-loaded and the watch-type bullets are useful, but pricing is repeated ('REGISTERING IS FREE', '$0 · Delivery after trial: $0.05', 'First 3 deliveries are free'), and asides like 'not a FRED-macro subscription' and 'This is retention, not a new data product' are editorial noise. Several sentences do not earn their place.

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 not be explained, and the description covers costs, limits, signing, and error behavior well. It omits lifecycle details an agent would want: idempotency of repeated registrations (annotations flag idempotent=false) and how to remove or update a subscription. Minor but real gaps for a subscription-creating tool.

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?

With schema coverage at 100%, the baseline is 3, but the description adds genuine meaning: it explains that series watches fire on value/effective-date movement (and contrasts statutory watches vs a FRED-macro subscription), that sources watches fire on document BYTES change with old/new sha256, and that api_key funds deliveries without being metered by this call. That goes meaningfully beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource (bind a webhook / register an alert) and spells out two watch types (series → series.changed, sources → source.changed). It even differentiates from the sibling get_changes. The opening sentence ('so the next gazette does not silently stale a value you already paid for') is indirect and marketing-flavored, delaying the actual purpose, which keeps it short of a 5.

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?

It explicitly routes the agent: 'Prefer this over polling get_changes if you are a long-running agent,' naming the alternative and the condition that selects it. It also implies the monitoring use case via the two watch types, but gives no explicit when-not guidance (e.g. one-shot checks or short-lived agents), so it falls short of full when/when-not coverage.

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

All euroref — European government 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?