Uk Parliament

Recent Divisions

recent_divisions

Read-onlyIdempotent

Recent divisions (recorded votes) in the UK Parliament, read from the official Hansard API at hansard-api.parliament.uk, filterable by house (Commons or Lords) and a start date, up to 25 per call. Returns each division title, date, house, and division id. Answers what the House of Commons or House of Lords has voted on lately at Westminster.

Input Schema

TableJSON Schema

Name	Required	Description
`take`	No	1-25 (default 25)
`house`	No	Commons \| Lords
`date_from`	No	YYYY-MM-DD

Output Schema

TableJSON Schema

Name	Required	Description	Default
`Results`	No
`TotalResultCount`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 24, 2026

addedOutput schema / properties / Results

Added value: +{
+  "items": {
+    "properties": {
+      "AyesCount": {
+        "type": "number"
+      },
+      "Date": {
+        "type": "string"
+      },
+      "DebateSection": {
+        "type": "string"
+      },
+      "DebateSectionExtId": {
+        "type": "string"
+      },
+      "DebateSectionSource": {
+        "type": "string"
+      },
+      "DivisionHasTime": {
+        "type": "boolean"
+      },
+      "EVELAyesCount": {
+        "type": "null"
+      },
+      "EVELInfo": {
+        "type": "null"
+      },
+      "EVELNoesCount": {
+        "type": "null"
+      },
+      "EVELType": {
+        "type": "null"
+      },
+      "ExternalId": {
+        "type": "string"
+      },
+      "House": {
+        "type": "string"
+      },
+      "Id": {
+        "type": "number"
+      },
+      "IsCommitteeDivision": {
+        "type": "boolean"
+      },
+      "MemberVotedAye": {
+        "type": "null"
+      },
+      "NoesCount": {
+        "type": "number"
+      },
+      "Number": {
+        "type": "string"
+      },
+      "TextAfterVote": {
+        "type": "string"
+      },
+      "TextBeforeVote": {
+        "type": "string"
+      },
+      "Time": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / TotalResultCount
```
Added value: +{
+  "type": "number"
+}
```

removedOutput schema / properties / divisions

Removed value: -{
-  "description": "List of recent division (vote) records",
-  "items": {
-    "description": "Individual division record",
-    "type": "object"
-  },
-  "type": "array"
-}

Changed2 schema fields changedMay 27, 2026

addedInput schema / examples

Added value: +[
+  {
+    "house": "Commons",
+    "take": 20
+  },
+  {
+    "date_from": "2024-01-01",
+    "house": "Lords"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Recent recorded parliamentary votes",
+  "properties": {
+    "divisions": {
+      "description": "List of recent division (vote) records",
+      "items": {
+        "description": "Individual division record",
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

First observedMay 13, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds context beyond those: it names the official Hansard API as the source, states the 25-per-call limit, and lists the returned fields. No contradiction with 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.

Conciseness4/5

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

The description is reasonably compact and front-loaded with the core concept. The first two sentences earn their place; the third sentence is somewhat redundant with the first but adds a user-focused purpose, so it is not wasted. Minor redundancy prevents a 5.

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?

The tool is simple, all three parameters are optional and fully described in the schema, an output schema exists, and annotations cover the behavioral safety profile. The description supplies the remaining context: the data source, response item fields, and call limit. Nothing essential is missing for an agent to call it correctly.

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?

Schema description coverage is 100%: take, house, and date_from are already documented with their constraints and formats. The description echoes these concepts ('filterable by house', 'start date', 'up to 25 per call') but does not add meaning beyond the schema, so the baseline of 3 is appropriate.

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 identifies a specific verb-resource relationship: retrieving recent divisions (recorded votes) in the UK Parliament. It adds useful detail about the source API, filters, and returned fields, making it distinct from related tools like search_hansard, get_bill, or bill_stages.

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 clearly implies when to use it: when the agent needs to answer what the Commons or Lords has recently voted on, with optional house and start-date filters. It does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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

All Uk Parliament 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.