Skip to main content
Glama

UK Legal Research

by io.github.paulieb89

Parse OSCOLA Citations

citations_parse
Read-only

USE THIS TOOL WHEN you have free text (a memo, an email, a clause) and want every OSCOLA-style citation it contains extracted and classified.

Identifies: neutral citations ([2024] UKSC 12), law reports ([2024] 1 WLR 100), legislation sections (s.47 Companies Act 2006), SIs (SI 2018/1234), retained EU law (Regulation (EU) 2016/679).

Parsing is pure regex by default. Ambiguous citations (e.g. bare [2024] EWHC without division) can OPTIONALLY be disambiguated by setting disambiguate=True, which asks the CONNECTED CLIENT's own model (not this server) to resolve the division via MCP sampling — off by default. Citations resolve to TNA / legislation.gov.uk URLs when possible.

AFTER calling, pass each citation through citations_resolve to verify it points at a real document before quoting or formatting it — the parser recognises the SHAPE of a citation but does not confirm the document exists.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesFree text containing OSCOLA citations to extract. Supported: neutral citations ([2024] UKSC 12), law reports ([2024] 1 WLR 100), legislation sections (s.47 Companies Act 2006), SIs (SI 2018/1234), retained EU law (Regulation (EU) 2016/679). Max 50,000 chars.
disambiguateNoDefault False — pure-regex parsing, no model in the loop. If True, ambiguous citations (e.g. bare EWHC without a division) are sent to the connected client's own LLM, via MCP sampling, to resolve the division. Opt in only when you want best-effort division resolution and accept that a model shapes the result.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
ambiguousYesCitations with confidence < 0.7; may have been partially disambiguated via sampling
citationsYesAll successfully parsed citations (confidence >= 0.7)
text_lengthYesCharacter length of the input text
parse_duration_msYesTime taken to parse, in milliseconds

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description adds critical behavioral context: parsing is pure regex by default, optional disambiguation invokes the client's own LLM via MCP sampling, and recognition of citation shape does not guarantee document existence. This meaningfully informs the agent of limitations and side effects (model-in-the-loop) that annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

The description is well-structured with clear sections: a bolded usage trigger, a list of supported citation types, parsing behavior, and a follow-up instruction. It is front-loaded with the most important 'when to use' information and every sentence contributes operational value without redundancies.

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?

Given the tool has only 2 parameters, an output schema, and rich sibling context, the description fully covers the essential operational details: input type, output scope, disambiguation behavior, URL resolution, and the requirement to verify via citations_resolve. It clearly differentiates itself from the resolve and format siblings, so an agent can select and invoke 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 coverage is 100%, and the parameter descriptions already fully explain the text and disambiguate parameters. The tool description repeats the supported citation types and the disambiguation behavior, adding little new semantic value beyond the schema. It does hint at URL resolution as output, but that is not a parameter-level detail.

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 opens with a specific action ('extract and classify every OSCOLA-style citation') and identifies the target resource (free text). It lists concrete citation types and explicitly separates itself from sibling tools like citations_resolve by stating what it does not do (confirm existence). The verb and scope are precise and unambiguous.

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 states when to use the tool ('USE THIS TOOL WHEN you have free text... and want every OSCOLA-style citation... extracted and classified') and explicitly directs the agent to follow up with citations_resolve for verification. It does not explicitly say when not to use it, but the alternative/next-step guidance is strong and actionable.

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

All UK Legal Research toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Every tool has a clearly distinct purpose, with detailed descriptions that prevent ambiguity. Tools covering similar domains (e.g., multiple parliament search tools) are carefully differentiated by their search approach and input requirements.

Naming Consistency5/5

All tools follow a consistent snake_case verb_noun pattern (e.g., bills_get_bill, case_law_search, citations_resolve). Even generic tools adhere to this style. No mixing of conventions.

Tool Count4/5

With 35 tools, the count is on the higher side but appropriate for the wide-ranging domain of UK legal research. Each tool contributes to specific sub-domains (bills, case law, citations, committees, HMRC, legislation, parliament, votes) without unnecessary duplication.

Completeness5/5

The tool surface covers nearly all essential aspects of UK legal research: searching and retrieving bills, case law, and legislation; parsing and resolving citations; exploring committee evidence; accessing Hansard debates and member interests; and checking HMRC guidance and VAT rates. Gaps like full judgment text retrieval are mitigated by paragraph-level access and indexing.

Resources