search_committee_debates

Search Hansard committee debates by keyword, house, committee title, or date range to find parliamentary discussions and evidence sessions.

Instructions

Search committee debates in Hansard | Hansard, committees, select committee debates | Use to find debates and discussions from parliamentary committees | Returns committee debates matching the search criteria

    Args:
        house: Optional: house - 1 or 'Commons', 2 or 'Lords'.
        start_date: Start date in YYYY-MM-DD format (optional).
        end_date: End date in YYYY-MM-DD format (optional).
        search_term: Search term (optional).
        committee_title: Filter by committee title (optional).
        skip: Number of results to skip for pagination (default 0).
        take: Number of results to return (default 20).

    Returns:
        Committee debates matching the search criteria.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`skip`	No
`take`	No
`house`	No
`end_date`	No
`start_date`	No
`search_term`	No
`committee_title`	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

B3.3/5.0

Behavior2/5

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 nothing about permissions, result ordering, or how partial matches behave, and the only behavioral detail (skip/take pagination) is restated from the schema defaults rather than adding new insight.

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?

Front-loaded purpose is good, but the header line and the Returns block both say 'committee debates matching the search criteria', which is redundant, and the pipe-separated keyword list adds bulk with limited routing value.

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?

An output schema exists, so return-value detail is not required, and the args block fully documents all seven parameters. The only gap is guidance on when to prefer this over the other Hansard search tools, which keeps it short of a 5.

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: it enumerates all seven parameters, gives the house enum values (1/'Commons', 2/'Lords'), the date format YYYY-MM-DD, and pagination defaults. It is the primary documentation source and does the job well.

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?

States a specific verb and resource ('Search committee debates in Hansard') with keyword tags clarifying domain. An agent can tell it retrieves committee debates, but the description does not distinguish it from near-siblings like search_hansard or search_hansard_committees, which cover overlapping ground.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use to find debates and discussions from parliamentary committees' gives an implied context but names no alternatives and no when-not conditions. With many search_* siblings, an agent is left to infer which search to pick.

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

Deploy Server

UK Parliament MCP Server