UK Parliament MCP Server

search_parliament

Search UK Parliament members, bills, committees, debates, and written questions in one call. Use when unsure which record type holds the answer; returns matches and next tool suggestions.

Instructions

Search across Parliament in one call - members, bills, committees, Hansard debates and written questions | search everything, find anything, cross-search, where is this mentioned, general search | Use as a starting point when you don't know which kind of record holds the answer | Returns the top matches and total counts for each kind of record, with the tool to call next for each. Combines: search_members, search_bills, search_committees, search_hansard_full, search_written_questions. See also: parliament_workflow (to plan a research approach).

    Args:
        query: Search text (e.g. 'Renters Rights', 'Starmer', 'Treasury', 'net zero').
        take: Number of top matches per kind of record (default 5).

    Returns:
        Per-category matches and totals.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`take`	No
`query`	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

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose meaningful traits: it is a fan-out aggregator over five sibling tools, and it returns 'the top matches and total counts for each kind of record, with the tool to call next for each.' It omits rate/cost implications of a cross-search and any pagination behavior, but the aggregation semantics are a genuine addition.

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 sentences are front-loaded and useful, but the 'search everything, find anything, cross-search, where is this mentioned, general search' clause is keyword padding that adds discovery aliases at the cost of clarity. Still readable, but a sentence that does not fully earn its place.

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 broad entry-point search tool, everything needed to invoke it correctly is present: scope, the record kinds covered, the composing siblings, the usage trigger, parameter meaning, and next-step routing. An output schema exists, so the description is not obliged to detail return shapes, and it still summarizes them.

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 0%, so the description must compensate, and it largely does: 'query' is illustrated with four concrete examples ('Renters Rights', 'Starmer', 'Treasury', 'net zero') and 'take' is defined as 'Number of top matches per kind of record (default 5),' which clarifies the per-category semantics beyond the bare integer 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 and resource ('Search across Parliament'), enumerates the five record kinds it spans, and explicitly names the sibling tools it combines (search_members, search_bills, search_committees, search_hansard_full, search_written_questions). An agent can distinguish this from the narrower per-domain search 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 a clear trigger condition: 'Use as a starting point when you don't know which kind of record holds the answer,' and routes to parliament_workflow for planning. It does not explicitly state when NOT to use it (e.g. use search_bills directly when the record type is already known), 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.

Deploy Server