Skip to main content
Glama

summarize_multiple_urls

Generate concise summaries of multiple web page URLs with AI. Input URLs and customize summarization instructions, format, and length for quick insights.

Instructions

Summarize multiple web page URLs using AI via ReviewWeb.site API.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
api_keyNoYour ReviewWebsite API key
debugNoWhether to enable debug mode
delayAfterLoadNoOptional delay after page load in milliseconds
formatNoFormat of the summary (bullet points or paragraph)
instructionsNoCustom instructions for the AI on how to summarize the content
maxLengthNoMaximum length of each summary in words
maxLinksNoMaximum number of URLs to process
modelNoAI model to use for summarization
systemPromptNoCustom system prompt to guide the AI
urlsYesList of URLs to summarize

Implementation Reference

  • Registers the MCP tool named 'summarize_multiple_urls' with the server, specifying the description, input schema from types, and the handler function.
    server.tool(
    	'summarize_multiple_urls',
    	`Summarize multiple web page URLs using AI via ReviewWeb.site API.`,
    	SummarizeMultipleUrlsToolArgs.shape,
    	handleSummarizeMultipleUrls,
    );
  • The main handler function for the 'summarize_multiple_urls' MCP tool. It logs the call, delegates to the ReviewWebsite controller's summarizeMultipleUrls method, formats the successful response as MCP content block, or returns formatted error.
    /**
     * @function handleSummarizeMultipleUrls
     * @description MCP Tool handler to summarize multiple URLs using AI
     * @param {SummarizeMultipleUrlsToolArgsType} args - Arguments provided to the tool
     * @returns {Promise<{ content: Array<{ type: 'text', text: string }> }>} Formatted response for the MCP
     */
    async function handleSummarizeMultipleUrls(
    	args: SummarizeMultipleUrlsToolArgsType,
    ) {
    	const methodLogger = Logger.forContext(
    		'tools/reviewwebsite.tool.ts',
    		'handleSummarizeMultipleUrls',
    	);
    	methodLogger.debug(`Summarizing multiple URLs with options:`, {
    		...args,
    		api_key: args.api_key ? '[REDACTED]' : undefined,
    	});
    
    	try {
    		const result = await reviewWebsiteController.summarizeMultipleUrls(
    			args.urls,
    			{
    				instructions: args.instructions,
    				systemPrompt: args.systemPrompt,
    				model: args.model,
    				delayAfterLoad: args.delayAfterLoad,
    				maxLinks: args.maxLinks,
    				maxLength: args.maxLength,
    				format: args.format,
    				debug: args.debug,
    			},
    			{
    				api_key: args.api_key,
    			},
    		);
    
    		return {
    			content: [
    				{
    					type: 'text' as const,
    					text: result.content,
    				},
    			],
    		};
    	} catch (error) {
    		methodLogger.error(`Error summarizing multiple URLs`, error);
    		return formatErrorForMcpTool(error);
    	}
    }
  • Zod schema defining the input arguments for the summarize_multiple_urls tool, including urls array and various optional summarization options.
    /**
     * Schema for ReviewWebsite summarize multiple URLs tool arguments
     */
    export const SummarizeMultipleUrlsToolArgs = z.object({
    	urls: z.array(z.string()).describe('List of URLs to summarize'),
    	instructions: z
    		.string()
    		.optional()
    		.describe(
    			'Custom instructions for the AI on how to summarize the content',
    		),
    	systemPrompt: z
    		.string()
    		.optional()
    		.describe('Custom system prompt to guide the AI'),
    	model: z.string().optional().describe('AI model to use for summarization'),
    	delayAfterLoad: z
    		.number()
    		.optional()
    		.describe('Optional delay after page load in milliseconds'),
    	maxLinks: z
    		.number()
    		.optional()
    		.describe('Maximum number of URLs to process'),
    	maxLength: z
    		.number()
    		.optional()
    		.describe('Maximum length of each summary in words'),
    	format: z
    		.enum(['bullet', 'paragraph'])
    		.optional()
    		.describe('Format of the summary (bullet points or paragraph)'),
    	debug: z.boolean().optional().describe('Whether to enable debug mode'),
    	api_key: z.string().optional().describe('Your ReviewWebsite API key'),
    });
  • Controller handler that wraps the service call to summarizeMultipleUrls, handles API key, logs, formats response as JSON string, and error handling.
    /**
     * @function summarizeMultipleUrls
     * @description Summarize multiple URLs using AI
     * @memberof ReviewWebsiteController
     * @param {string[]} urls - URLs to summarize
     * @param {SummarizeOptions} summarizeOptions - Summarization options
     * @param {ReviewWebsiteOptions} options - Options including API key
     * @returns {Promise<ControllerResponse>} A promise that resolves to the standard controller response
     * @throws {McpError} Throws an McpError if the service call fails or returns an error
     */
    async function summarizeMultipleUrls(
    	urls: string[],
    	summarizeOptions?: SummarizeOptions,
    	options: ReviewWebsiteOptions = {},
    ): Promise<ControllerResponse> {
    	const methodLogger = Logger.forContext(
    		'controllers/reviewwebsite.controller.ts',
    		'summarizeMultipleUrls',
    	);
    
    	methodLogger.debug('Summarizing multiple URLs', { urls, summarizeOptions });
    
    	try {
    		const apiKey = getApiKey(options);
    		const result = await reviewWebsiteService.summarizeMultipleUrls(
    			urls,
    			summarizeOptions,
    			apiKey,
    		);
    
    		return {
    			content: JSON.stringify(result, null, 2),
    		};
    	} catch (error) {
    		return handleControllerError(error, {
    			entityType: 'Summaries',
    			operation: 'creating',
    			source: 'controllers/reviewwebsite.controller.ts@summarizeMultipleUrls',
    			additionalInfo: { urlCount: urls.length },
    		});
    	}
    }
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 burden of behavioral disclosure. It mentions the tool uses AI via an external API, which implies it might involve network calls, potential rate limits, or authentication needs, but it doesn't explicitly state these traits. For example, it doesn't clarify if the tool is read-only, destructive, or has any performance constraints, leaving significant gaps in behavioral understanding.

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 a single, efficient sentence: 'Summarize multiple web page URLs using AI via ReviewWeb.site API.' It is front-loaded with the core purpose, uses clear language, and avoids unnecessary details. Every word earns its place, making it highly concise and well-structured for quick understanding.

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

Completeness3/5

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

Given the complexity of 10 parameters and no annotations or output schema, the description is minimally adequate. It states the tool's purpose but lacks details on behavioral traits, usage context, or output format. For a tool with many parameters and external API dependencies, more information would be helpful, but the description meets a basic threshold without being misleading.

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?

The input schema has 100% description coverage, meaning all parameters are documented in the schema itself. The description adds no additional meaning beyond the schema, such as explaining parameter interactions or providing examples. With high schema coverage, the baseline score is 3, as the description doesn't compensate but also doesn't detract from the schema's completeness.

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?

The description clearly states the tool's purpose: 'Summarize multiple web page URLs using AI via ReviewWeb.site API.' It specifies the verb ('summarize'), resource ('multiple web page URLs'), and method ('using AI via ReviewWeb.site API'), which is clear and specific. However, it doesn't explicitly distinguish this tool from sibling tools like 'summarize_url' or 'summarize_website', which likely have overlapping functionality, so it doesn't reach the highest score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'summarize_url' (for single URLs) or 'summarize_website' (which might handle entire sites), nor does it specify prerequisites such as needing an API key or when this tool is preferred over other summarization methods. This lack of context leaves the agent without clear usage instructions.

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

Related 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/mrgoonie/reviewwebsite-mcp-server'

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