UK Parliament MCP Server

search_written_questions

Search UK parliamentary written questions by keyword, MP, department, date, house, or answer status to track government responses and research accountability.

Instructions

Search written parliamentary questions with comprehensive filtering | written questions, PQs, parliamentary questions, questions to ministers, government accountability | Use for researching MP activity, tracking government responses, analyzing ministerial accountability, or finding questions on specific topics | Returns questions with asking member, answering body, dates, and response status See also: get_written_question, search_written_statements, get_answering_bodies.

    Args:
        search_term: Text to search for in question content.
        asking_member_id: Filter by the member ID who asked the question.
        answering_body_id: Filter by the government department that answered.
        answered: Filter by answer status: "Any", "Answered", or "Unanswered".
        tabled_from: Start date for when question was tabled (YYYY-MM-DD).
        tabled_to: End date for when question was tabled (YYYY-MM-DD).
        house: Filter by house: 'Commons', 'Lords' or 'Bicameral' (1 or 2 also accepted).
        skip: Number of records to skip for pagination. Default: 0.
        take: Number of records to return. Default: 20.

    Returns:
        Written questions matching the search criteria with member, department, and answer details.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`skip`	No
`take`	No
`house`	No
`answered`	No
`tabled_to`	No
`search_term`	No
`tabled_from`	No
`asking_member_id`	No
`answering_body_id`	No

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

A4.2/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the return fields (asking member, answering body, dates, response status) and pagination controls, but says nothing about sorting order, maximum page size, permissions, or result caps. Adequate but with clear gaps for an unannotated search tool.

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 purpose and routing are front-loaded before the Args block, and the parameter documentation is dense and useful. The pipe-delimited keyword block ('written questions, PQs, parliamentary questions, questions to ministers, government accountability') is mildly redundant padding, but overall the text earns its space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain returns, and it still summarizes them briefly. All nine parameters are covered and alternatives are named, so an agent has enough to invoke correctly; only minor operational details (sort order, page-size ceiling) are absent.

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% and no enums exist, so the description must compensate entirely — and it does. It documents all nine parameters with real meaning, including enum values for 'answered' (Any/Answered/Unanswered), accepted forms for 'house' ('Commons', 'Lords', 'Bicameral', or 1/2), the YYYY-MM-DD date format, and defaults for skip/take.

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 written parliamentary questions with comprehensive filtering') and explicitly lists sibling tools (get_written_question, search_written_statements, get_answering_bodies) so the agent can distinguish a bulk search from a single-record lookup. The 'written questions, PQs, parliamentary questions' keyword block further disambiguates terminology.

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 use contexts ('researching MP activity, tracking government responses, analyzing ministerial accountability, or finding questions on specific topics') and routes to alternatives via 'See also'. It lacks an explicit when-not statement (e.g., use get_written_question for a single UIN), but the alternative naming covers most routing needs.

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

Deploy Server