Afriref: cited government reference data

Statutory filing deadlines

get_filing_deadlines

Read-onlyIdempotent

PAID ($0.003, same as any series). Recurring statutory tax deadlines for a country — VAT/GST returns and payments, PAYE/payroll withholding remittances, corporate income tax returns and provisional/instalment payments — as RULES, each cited to the official source with the verbatim phrase that states it, plus the actual DUE DATES in a window, rolled for the country's weekend and national public holidays (every skipped day is listed). Where a rule's source does not say which way a weekend deadline moves, the date is flagged roll_unverified rather than guessed. Countries or taxes we could not verify are returned as a free coverage_gap with reasons, never invented. Pass year_end (MM-DD) to re-anchor corporate-tax rules on the company's own accounting year end. The HTML page /{country}/filing-deadlines shows the rules free. Every GH series is free to try. After a 200, bind get_changes (free poll) or register_alert (HMAC push; Register: $0 · Delivery after trial: $0.05) on this series so a later gazette does not silently retire the value.

Input Schema

Name	Required	Description
`to`	No	Window end, YYYY-MM-DD. Default from + 365 days; at most 400 days after from
`tax`	No	Only this tax's rules and dates
`from`	No	Window start, YYYY-MM-DD. Default today
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code
`year_end`	No	Company accounting year end, MM-DD (e.g. 06-30). Applies to rules marked year_end_variable

Output Schema

Name	Required	Description
`gaps`	No
`unit`	No
`error`	No	Present on a free refusal or error; no charge
`notes`	No
`stale`	No
`value`	No	The rules. Each carries its own source {name, url, anchor} and last_confirmed
`series`	No
`source`	No
`status`	No	On a coverage gap: researched_no_verified_rule or not_yet_researched
`country`	No
`due_dates`	No	Computed occurrences in the window, sorted by due_date
`no_charge`	No
`price_usd`	No
`confidence`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`coverage_gaps`	No	Taxes in scope with no verified rule for this country, and why
`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
`effective_from`	No
`last_confirmed`	No
`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
`computed_disclaimer`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 17, 2026
- 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"
+]
```
AddedOct 13, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial behavioral context beyond them: pricing, holiday and weekend rolling with every skipped day listed, the roll_unverified flag instead of guessing, coverage_gap for unverifiable countries with explicit 'never invented' guarantee, and post-response polling/alert guidance. That is materially richer than the annotations.

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 purpose is front-loaded and dense with useful detail, but the description is padded with pricing/marketing text ('PAID ($0.003, same as any series)', 'Every GH series is free to try', the register_alert price breakdown) that does not help an agent select or invoke the tool. Several sentences earn their place; several do not.

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 six-parameter, high-complexity tool with an output schema and annotations present, the description covers what an agent needs: scope, the year_end re-anchoring behavior, integrity flags (roll_unverified, coverage_gap), and follow-up polling. Return-value shapes are handled by the output schema, so nothing critical 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 description coverage is 100%, so the baseline is 3. The description adds real meaning for year_end (re-anchors corporate-tax rules on the company's accounting year end, targeting year_end_variable rules) and reinforces the from/to window semantics and the tax filter. This exceeds what the schema alone conveys, though most parameters remain fully documented in the schema.

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+resource: recurring statutory tax deadlines for a country, and enumerates the content precisely (VAT/GST returns and payments, PAYE remittances, CIT returns and provisional instalments) as cited RULES plus rolled DUE DATES. This is clearly distinguishable from calculation siblings like compute_vat or compute_statutory_interest, which produce amounts rather than deadlines. An agent can identify the tool's output shape without opening the 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?

Gives clear context for optional behavior (pass year_end to re-anchor corporate-tax rules) and for follow-up actions (bind get_changes to poll, register_alert for HMAC push after a 200), plus a free alternative view via the HTML page. It does not explicitly say when to prefer this over sibling tax tools or name any exclusion, 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 Afriref: cited 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?