canada-law
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find_actA | Find acts and regulations by title. Returns candidates with act_id (pass it to get_toc and get_section), the official title, citation (e.g. "RSBC 1996, c. 113" or "B.C. Reg. 396/95"; federal "R.S.C., 1985, c. L-2" or "C.R.C., c. 986"), source_url, and for BC acts whether they are current or repealed/replaced. Exact title matches come first. Federal titles come from the official list of acts and regulations, which does not mark repealed acts: get_toc and get_section say when an act is repealed. |
| get_tocA | Table of contents of an act or regulation: Parts, Divisions and Schedules with every section number and heading, plus the act's citation, source_url and official current_to date. Use it to pick the right section number before calling get_section. The result also carries answer_rules, the answer format and rules for using this text: follow them when you answer. |
| get_sectionA | Verbatim text of one section, laid out as on the official page (subsections, paragraphs, definitions), with the full citation: act_title, act_citation, act_id, section, heading, source_url (links to the section), current_to (the official "current to" date) and retrieved_at. Quote this text rather than paraphrasing it as the law. The result also carries answer_rules, the answer format and rules for using this text: follow them when you answer. |
| search_lawA | Search current legislation for English statutory wording and get the matching sections, best first, each with citation fields (act, section, heading, source_url, current_to) and a snippet. The query must use the statutory English of the jurisdiction: if the question is in Chinese or uses everyday words, call map_term first (for example BC says "statutory holiday" where federal law says "general holiday"). Then read the full text with get_section before answering. The result also carries answer_rules, the answer format and rules for using this text: follow them when you answer. |
| map_termA | Map a Chinese (or everyday English) employment-law concept to the statutory English each jurisdiction uses, BC and federal, and where it appears (act_id and sections). Call this before search_law when the question is in Chinese or uses everyday words, and search each jurisdiction with its own terms. Returns [] when the term is not in the curated glossary: then do not present your own translation as the statutory term; try a more basic term, or search with your own English wording and say that you did. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct stage of the workflow: terminology mapping, act discovery, table of contents, section retrieval, and full-text search. The descriptions explicitly spell out the boundaries (e.g. call map_term before search_law, use get_toc to pick a section before get_section). No two tools could plausibly be confused for each other.
All five tools follow a strict verb_noun snake_case pattern: map_term, find_act, get_toc, get_section, search_law. The convention is uniform and predictable across the set.
Five tools is well-scoped for a legislation lookup server; each tool earns its place in a clear pipeline from term mapping to section retrieval. Nothing feels redundant or missing at the count level.
The surface covers the core lifecycle: find acts/regulations, browse structure, read sections verbatim, and search statutory wording, including handling of repealed acts and citation metadata. Minor gaps exist (no explicit list/browse-by-jurisdiction tool or case-law coverage), but agents can work around these via find_act and search_law.