UK Parliament MCP Server

compare_member_votes

Compare two MPs' or Lords' voting records division by division to see agreement counts, rates, rebels, and party loyalty. Use for head-to-head voting similarity overall or by topic.

Instructions

Compare how two MPs (or two Lords) voted - lines up their votes division by division | compare voting records, do they agree, voting similarity, rebels, party loyalty, head to head | Use when asked whether two members vote the same way, overall or on a topic | Returns both members, agreement counts and rate, each shared division with both votes, and divisions only one of them voted in. Combines: get_member_by_id (x2), get_commons_voting_record_for_member or get_lords_voting_record_for_member (x2). See also: check_mp_vote, get_commons_divisions_grouped_by_party.

    Args:
        member_id_a: First member's Parliament ID. Get from get_member_by_name. Example: 4514
        member_id_b: Second member's Parliament ID; must sit in the same House as the first.
        topic: Optional: only divisions whose title matches this topic (e.g. 'climate', 'Rwanda').
        take: Number of each member's most recent matching divisions to compare (default 50, max 100).

    Returns:
        Agreement summary and division-by-division comparison.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`take`	No
`topic`	No
`member_id_a`	Yes
`member_id_b`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the composite implementation (combines get_member_by_id x2 and the voting-record calls x2), the same-House constraint on member_id_b, and the full return shape (agreement counts/rate, shared divisions, single-member divisions). It omits read-only/permission context and any rate-limit or cost notes, keeping it short of a 5.

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 sentence is front-loaded and the Args/Returns sections are well organized, but the keyword block ('compare voting records, do they agree, voting similarity, rebels, party loyalty, head to head') is SEO-style padding that restates the same idea several times without adding selection signal.

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 comparison tool whose output schema already documents the return values, the description supplies everything an agent needs to call it correctly: both IDs, the same-House constraint, topic filtering, and the take window, plus the composite-call behavior. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate and it does fully: it explains member_id_a's source and gives a concrete example (4514), states member_id_b's same-House requirement, defines topic with matching examples, and specifies take's default (50) and max (100).

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 ('Compare how two MPs ... voted - lines up their votes division by division') and names the sibling tools it is not (check_mp_vote, get_commons_divisions_grouped_by_party). An agent can distinguish this from the single-member voting-record tools 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?

Gives an explicit trigger ('Use when asked whether two members vote the same way, overall or on a topic') and routes to related siblings via 'See also'. It stops short of stating when NOT to use it or listing alternative tools the agent should prefer in edge cases, so it is clear but not exhaustive.

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

Deploy Server