Skip to main content
Glama

Get Case Citations

get_case_citations
Read-only

Retrieve citation relationships for a Canadian case: get cases it cites, cases citing it, or legislation it references using case ID and database ID.

Instructions

Get citation information for a case: what it cites, what cites it, or what legislation it references. Note: the CanLII API currently only supports English for this endpoint; French requests will fall back to English.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
caseIdYesCase ID (e.g. "1999canlii1527")
citationTypeYesType of citation data to retrieve
databaseIdYesDatabase ID (e.g. "onca")
languageNoResponse language (currently only 'en' is supported by the API)en

Implementation Reference

  • src/server.ts:208-235 (registration)
    Registration of the 'get_case_citations' tool via server.registerTool, defining its metadata and handler.
    // 4. Case citator
    server.registerTool(
    	"get_case_citations",
    	{
    		annotations: { readOnlyHint: true },
    		description:
    			"Get citation information for a case: what it cites, what cites it, or what legislation it references. Note: the CanLII API currently only supports English for this endpoint; French requests will fall back to English.",
    		inputSchema: {
    			caseId: z.string().describe('Case ID (e.g. "1999canlii1527")'),
    			citationType: z
    				.enum(["citedCases", "citingCases", "citedLegislations"])
    				.describe("Type of citation data to retrieve"),
    			databaseId: z.string().describe('Database ID (e.g. "onca")'),
    			language: z
    				.enum(["en", "fr"])
    				.default("en")
    				.describe("Response language (currently only 'en' is supported by the API)"),
    		},
    		title: "Get Case Citations",
    	},
    	async ({ databaseId, caseId, citationType }) => {
    		try {
    			return ok(await request(`/caseCitator/en/${databaseId}/${caseId}/${citationType}`));
    		} catch (e) {
    			return err(String(e));
    		}
    	},
    );
  • Input schema for 'get_case_citations' with caseId, citationType, databaseId, and language parameters using Zod validation.
    {
    	annotations: { readOnlyHint: true },
    	description:
    		"Get citation information for a case: what it cites, what cites it, or what legislation it references. Note: the CanLII API currently only supports English for this endpoint; French requests will fall back to English.",
    	inputSchema: {
    		caseId: z.string().describe('Case ID (e.g. "1999canlii1527")'),
    		citationType: z
    			.enum(["citedCases", "citingCases", "citedLegislations"])
    			.describe("Type of citation data to retrieve"),
    		databaseId: z.string().describe('Database ID (e.g. "onca")'),
    		language: z
    			.enum(["en", "fr"])
    			.default("en")
    			.describe("Response language (currently only 'en' is supported by the API)"),
    	},
    	title: "Get Case Citations",
    },
  • Handler function for 'get_case_citations' that makes a GET request to /caseCitator/en/{databaseId}/{caseId}/{citationType} and returns the JSON result.
    async ({ databaseId, caseId, citationType }) => {
    	try {
    		return ok(await request(`/caseCitator/en/${databaseId}/${caseId}/${citationType}`));
    	} catch (e) {
    		return err(String(e));
    	}
    },
  • The canliiRequest helper that performs the actual HTTP call to the CanLII API with rate limiting and error handling.
    async function canliiRequest(
    	apiKey: string,
    	path: string,
    	params: Record<string, string> = {},
    ): Promise<unknown> {
    	await acquireSlot();
    	try {
    		const url = new URL(`${BASE_URL}${path}`);
    		url.searchParams.set("api_key", apiKey);
    		for (const [k, v] of Object.entries(params)) {
    			if (v !== undefined && v !== "") url.searchParams.set(k, v);
    		}
    		const res = await fetch(url.toString());
    		if (!res.ok) {
    			const body = await res.text();
    			throw new Error(`CanLII API ${res.status}: ${body}`);
    		}
    		return await res.json();
    	} finally {
    		releaseSlot();
    	}
    }
  • Helper functions ok() and err() that format successful/error responses for tool output.
    type ToolResult = {
    	content: Array<{ type: "text"; text: string }>;
    	isError?: boolean;
    };
    
    function ok(data: unknown): ToolResult {
    	return { content: [{ text: JSON.stringify(data, null, 2), type: "text" }] };
    }
    
    function err(message: string): ToolResult {
    	return { content: [{ text: message, type: "text" }], isError: true };
    }
Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description adds behavioral context (language fallback behavior) that annotations do not cover. No contradiction.

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?

Two short, clear sentences. Every sentence adds value. No unnecessary words.

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?

For a 4-param tool with no output schema, the description covers purpose and a key behavioral note. Slight gap on response format, but adequate given simplicity.

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 description coverage is 100%, so baseline is 3. The description does not add significant meaning beyond summarizing the enum values and noting language limit.

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 clearly states the verb 'Get' and resource 'citation information for a case', and lists the three types of citations (what it cites, what cites it, legislation). This distinguishes it from sibling tools like get_case and get_legislation.

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?

It includes a critical usage note about language fallback, but does not explicitly contrast with sibling tools or provide when-to-use/alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Vaquill-AI/canlii-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server