Ärikratt

Risk signals

risk_signals

Read-only

Legal entities matching tax debt, bankruptcy, liquidation, enforcement, restructuring or distress signals. Use cursor pagination for company lists. kind=tax_debt_trend returns observed monthly debt stock, joined/left observations and latest active-cohort sector/county incidence: top 10 by incidence rate. Estonian Classification of Economic Activities (EMTAK) and county filters affect incidence rows only; both return separate aggregates. Sector codes map to two-digit divisions; shorter prefixes match divisions. Trends have no cursor; newest months are retained with totals and truncation flags. Baselines and gaps are excluded. Absence is not debt-free; scheduled and disputed amounts remain separate. Amounts withheld below 100 EUR or source-suppressed differ from zero or no published list. Estonian Tax and Customs Board (EMTA) attribution accompanies results; old snapshots return empty lists. Use check_counterparty for one code. Do not look up natural persons.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	tax_debt_trend (national months; county/emtak filter incidence), tax_debt, bankruptcy, liquidation, enforcement, restructuring, distress_high, or distress_moderate
`emtak`	No	Estonian Classification of Economic Activities (EMTAK) code or prefix
`limit`	No	At most 25 signals
`county`	No	County name or alias. Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maakond, Rapla maakond, Saare maakond, Tartu maakond, Valga maakond, Viljandi maakond, Võru maakond, Maakond puudu.
`cursor`	No	Opaque cursor from a previous next_cursor for the next page

Output Schema

TableJSON Schema

Name	Required	Description
`end`	No
`hint`	No	Trend incidence ranking and county/emtak filter guidance for fetching omitted rows.
`note`	No
`as_of`	Yes
`scope`	No
`start`	No
`cohort`	No
`months`	No
`signals`	No
`sources`	Yes
`incidence`	No	Top incidence rates across counties and sectors, or rows selected by county/emtak. Both filters select separate aggregate rows, not a county-sector intersection. Months remain national.
`row_count`	No
`truncated`	No
`disclaimer`	Yes
`next_cursor`	No
`snapshot_id`	Yes
`cohort_as_of`	No
`missing_days`	No
`months_total`	No	Number of months in the full national history before size budgeting.
`observed_days`	No
`threshold_eur`	No
`incidence_top_n`	No	Actual number of incidence rows returned, ranked by share_pct descending, unknown rates last; at most 10 and possibly fewer under the 8,000-byte envelope.
`incidence_total`	No	Number of incidence rows matching county/emtak filters, or all rows when unfiltered, before top-N selection.
`months_returned`	No	Number of returned months; newest months are retained in chronological order.
`incidence_cohort`	No
`months_truncated`	No	True when oldest months were omitted to fit the 8,000-byte envelope.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 10, 2026
- addedOutput schema / properties / signals / items / properties / bankruptcy_phase
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```

Changed1 schema field changedOct 10, 2026

changedInput schema / properties / emtak / description

Previous value: -"EMTAK code or prefix"New value: +"Estonian Classification of Economic Activities (EMTAK) code or prefix"

Changed22 schema fields changedOct 5, 2026

changedInput schema / properties / kind / description

Previous value: -"tax_debt, bankruptcy, liquidation, enforcement, restructuring, distress_high, or distress_moderate"New value: +"tax_debt_trend (national months; county/emtak filter incidence), tax_debt, bankruptcy, liquidation, enforcement, restructuring, distress_high, or distress_moderate"

addedOutput schema / properties / cohort

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / cohort_as_of

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / end

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / hint

Added value: +{
+  "description": "Trend incidence ranking and county/emtak filter guidance for fetching omitted rows.",
+  "type": "string"
+}

addedOutput schema / properties / incidence

Added value: +{
+  "description": "Top incidence rates across counties and sectors, or rows selected by county/emtak. Both filters select separate aggregate rows, not a county-sector intersection. Months remain national.",
+  "items": {
+    "additionalProperties": true,
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "companies": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "denominator": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "dimension": {
+        "enum": [
+          "county",
+          "sector"
+        ]
+      },
+      "share_pct": {
+        "type": [
+          "number",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / incidence_cohort

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / incidence_top_n

Added value: +{
+  "description": "Actual number of incidence rows returned, ranked by share_pct descending, unknown rates last; at most 10 and possibly fewer under the 8,000-byte envelope.",
+  "maximum": 10,
+  "minimum": 0,
+  "type": "integer"
+}

addedOutput schema / properties / incidence_total

Added value: +{
+  "description": "Number of incidence rows matching county/emtak filters, or all rows when unfiltered, before top-N selection.",
+  "type": "integer"
+}

addedOutput schema / properties / missing_days
```
Added value: +{
+  "type": "integer"
+}
```

addedOutput schema / properties / months

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "properties": {
+      "companies": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "compared_days": {
+        "type": "integer"
+      },
+      "date": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "debt_amount": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "debt_amount_reason": {
+        "description": "withheld (below €100 or source-suppressed); no_list_published = no list published; null = numeric amount available, including zero.",
+        "enum": [
+          "withheld",
+          "no_list_published",
+          null
+        ]
+      },
+      "disputed_amount": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "disputed_amount_reason": {
+        "description": "withheld (below €100 or source-suppressed); no_list_published = no list published; null = numeric amount available, including zero.",
+        "enum": [
+          "withheld",
+          "no_list_published",
+          null
+        ]
+      },
+      "joined": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "left_count": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "missing_days": {
+        "type": "integer"
+      },
+      "month": {
+        "type": "string"
+      },
+      "observed_days": {
+        "type": "integer"
+      },
+      "scheduled_amount": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "scheduled_amount_reason": {
+        "description": "withheld (below €100 or source-suppressed); no_list_published = no list published; null = numeric amount available, including zero.",
+        "enum": [
+          "withheld",
+          "no_list_published",
+          null
+        ]
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / months_returned

Added value: +{
+  "description": "Number of returned months; newest months are retained in chronological order.",
+  "type": "integer"
+}

addedOutput schema / properties / months_total

Added value: +{
+  "description": "Number of months in the full national history before size budgeting.",
+  "type": "integer"
+}

addedOutput schema / properties / months_truncated

Added value: +{
+  "description": "True when oldest months were omitted to fit the 8,000-byte envelope.",
+  "type": "boolean"
+}

addedOutput schema / properties / note

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / observed_days
```
Added value: +{
+  "type": "integer"
+}
```

addedOutput schema / properties / scope

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / sources / items / properties / licence_checked_at
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
addedOutput schema / properties / sources / items / properties / licence_evidence_url
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
addedOutput schema / properties / sources / items / properties / rights_status
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```

addedOutput schema / properties / start

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / threshold_eur
```
Added value: +{
+  "type": "integer"
+}
```

Changed1 schema field changedSep 27, 2026

changedInput schema / properties / kind / description

Previous value: -"tax_debt, bankruptcy, liquidation, distress_high, or distress_moderate"New value: +"tax_debt, bankruptcy, liquidation, enforcement, restructuring, distress_high, or distress_moderate"

Changed1 schema field changedSep 27, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "as_of": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "disclaimer": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "next_cursor": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "row_count": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "signals": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "amount": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "amount_unit": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "county": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "emtak_code": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "event_date": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "kind": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "label": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "registry_code": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "risk_level": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "score": {
+            "type": [
+              "number",
+              "null"
+            ]
+          }
+        },
+        "type": [
+          "object",
+          "null"
+        ]
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "snapshot_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "sources": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "attribution": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "licence": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "licence_url": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": [
+          "object",
+          "null"
+        ]
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "truncated": {
+      "type": [
+        "boolean",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "snapshot_id",
+    "as_of",
+    "sources",
+    "disclaimer"
+  ],
+  "title": "risk_signalsOutput",
+  "type": "object"
+}

First observedSep 26, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With annotations already covering the safety profile (readOnly, non-destructive, closed-world), the description goes well beyond them: cursor pagination applies to company lists but trends have no cursor, newest months are retained with truncation flags, baselines/gaps are excluded, amounts below 100 EUR or source-suppressed differ from zero, and stale snapshots return empty lists. This is exactly the kind of edge-case disclosure that prevents misreads of empty results.

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?

Purpose and the check_counterparty routing are front-loaded, and nearly every sentence carries distinct operational information (pagination, cursor asymmetry, truncation, withheld amounts). The style is telegraphic and some caveats are stacked densely, which slightly hurts readability, but there is little filler.

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 complex multi-kind tool with five optional parameters and an output schema, the description covers the behavioral gaps that matter: filter scoping, pagination asymmetry, retention/truncation, empty-result interpretation, and attribution. Return-value shape is delegated appropriately to the output schema.

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 genuine semantics: it explains that emtak sector codes map to two-digit divisions and that shorter prefixes match divisions, and that emtak/county filters affect incidence rows only while returning separate aggregates. That is meaning the schema does not carry.

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 opening sentence names the resource and the exact signal categories it surfaces (tax debt, bankruptcy, liquidation, enforcement, restructuring, distress), so an agent knows precisely what class of entities this returns. It stops short of a clean verb+resource framing, but the scope is unambiguous and it explicitly distances itself from check_counterparty.

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 gives a concrete alternative ('Use check_counterparty for one code') and an explicit exclusion ('Do not look up natural persons'), which is stronger than most list tools. It does not, however, explain how it relates to sibling list tools such as find_companies or search_companies, so the routing guidance is good but not exhaustive.

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

All Ärikratt 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?