Skip to main content
Glama

web_data_booking_hotel_listings

Extract structured hotel listings data from Booking.com URLs for reliable data collection without scraping.

Instructions

Quickly read structured booking hotel listings data. Requires a valid booking hotel listing URL. This can be a cache lookup, so it can be more reliable than scraping

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes

Implementation Reference

  • Core handler logic: Triggers BrightData dataset collection via API with the input URL, polls the snapshot status up to 600 times (1s intervals), returns JSON-stringified data when ready or throws timeout/error.
    execute: tool_fn(`web_data_${id}`, async(data, ctx)=>{
        let trigger_response = await axios({
            url: 'https://api.brightdata.com/datasets/v3/trigger',
            params: {dataset_id, include_errors: true},
            method: 'POST',
            data: [data],
            headers: api_headers(),
        });
        if (!trigger_response.data?.snapshot_id)
            throw new Error('No snapshot ID returned from request');
        let snapshot_id = trigger_response.data.snapshot_id;
        console.error(`[web_data_${id}] triggered collection with `
            +`snapshot ID: ${snapshot_id}`);
        let max_attempts = 600;
        let attempts = 0;
        while (attempts < max_attempts)
        {
            try {
                if (ctx && ctx.reportProgress)
                {
                    await ctx.reportProgress({
                        progress: attempts,
                        total: max_attempts,
                        message: `Polling for data (attempt `
                            +`${attempts + 1}/${max_attempts})`,
                    });
                }
                let snapshot_response = await axios({
                    url: `https://api.brightdata.com/datasets/v3`
                        +`/snapshot/${snapshot_id}`,
                    params: {format: 'json'},
                    method: 'GET',
                    headers: api_headers(),
                });
                if (['running', 'building'].includes(snapshot_response.data?.status))
                {
                    console.error(`[web_data_${id}] snapshot not ready, `
                        +`polling again (attempt `
                        +`${attempts + 1}/${max_attempts})`);
                    attempts++;
                    await new Promise(resolve=>setTimeout(resolve, 1000));
                    continue;
                }
                console.error(`[web_data_${id}] snapshot data received `
                    +`after ${attempts + 1} attempts`);
                let result_data = JSON.stringify(snapshot_response.data);
                return result_data;
            } catch(e){
                console.error(`[web_data_${id}] polling error: `
                    +`${e.message}`);
                attempts++;
                await new Promise(resolve=>setTimeout(resolve, 1000));
            }
        }
        throw new Error(`Timeout after ${max_attempts} seconds waiting `
            +`for data`);
    }),
  • Tool-specific configuration: id 'booking_hotel_listings', associated BrightData dataset_id, multi-line description, and required inputs ['url']. Used to build schema and handler.
    {
        id: 'booking_hotel_listings',
        dataset_id: 'gd_m5mbdl081229ln6t4a',
        description: [
            'Quickly read structured booking hotel listings data.',
            'Requires a valid booking hotel listing URL.',
            'This can be a cache lookup, so it can be more reliable than scraping',
        ].join('\n'),
        inputs: ['url'],
    }, {
  • server.js:683-744 (registration)
    Registers the tool named `web_data_${id}` (i.e., 'web_data_booking_hotel_listings') with Zod schema, description from config, and execute handler. Part of loop over all datasets.
    addTool({
        name: `web_data_${id}`,
        description,
        parameters: z.object(parameters),
        execute: tool_fn(`web_data_${id}`, async(data, ctx)=>{
            let trigger_response = await axios({
                url: 'https://api.brightdata.com/datasets/v3/trigger',
                params: {dataset_id, include_errors: true},
                method: 'POST',
                data: [data],
                headers: api_headers(),
            });
            if (!trigger_response.data?.snapshot_id)
                throw new Error('No snapshot ID returned from request');
            let snapshot_id = trigger_response.data.snapshot_id;
            console.error(`[web_data_${id}] triggered collection with `
                +`snapshot ID: ${snapshot_id}`);
            let max_attempts = 600;
            let attempts = 0;
            while (attempts < max_attempts)
            {
                try {
                    if (ctx && ctx.reportProgress)
                    {
                        await ctx.reportProgress({
                            progress: attempts,
                            total: max_attempts,
                            message: `Polling for data (attempt `
                                +`${attempts + 1}/${max_attempts})`,
                        });
                    }
                    let snapshot_response = await axios({
                        url: `https://api.brightdata.com/datasets/v3`
                            +`/snapshot/${snapshot_id}`,
                        params: {format: 'json'},
                        method: 'GET',
                        headers: api_headers(),
                    });
                    if (['running', 'building'].includes(snapshot_response.data?.status))
                    {
                        console.error(`[web_data_${id}] snapshot not ready, `
                            +`polling again (attempt `
                            +`${attempts + 1}/${max_attempts})`);
                        attempts++;
                        await new Promise(resolve=>setTimeout(resolve, 1000));
                        continue;
                    }
                    console.error(`[web_data_${id}] snapshot data received `
                        +`after ${attempts + 1} attempts`);
                    let result_data = JSON.stringify(snapshot_response.data);
                    return result_data;
                } catch(e){
                    console.error(`[web_data_${id}] polling error: `
                        +`${e.message}`);
                    attempts++;
                    await new Promise(resolve=>setTimeout(resolve, 1000));
                }
            }
            throw new Error(`Timeout after ${max_attempts} seconds waiting `
                +`for data`);
        }),
    });
  • Dynamically generates Zod input schema from inputs array and defaults. For this tool: z.object({ url: z.string().url() }).
    let parameters = {};
    for (let input of inputs)
    {
        let param_schema = input=='url' ? z.string().url() : z.string();
        parameters[input] = defaults[input] !== undefined ?
            param_schema.default(defaults[input]) : param_schema;
    }
  • Helper wrapper around tool execute functions: adds rate limiting, stats tracking, logging input/output/errors, timing, and propagates exceptions.
    function tool_fn(name, fn){
        return async(data, ctx)=>{
            check_rate_limit();
            debug_stats.tool_calls[name] = debug_stats.tool_calls[name]||0;
            debug_stats.tool_calls[name]++;
            debug_stats.session_calls++;
            let ts = Date.now();
            console.error(`[%s] executing %s`, name, JSON.stringify(data));
            try { return await fn(data, ctx); }
            catch(e){
                if (e.response)
                {
                    console.error(`[%s] error %s %s: %s`, name, e.response.status,
                        e.response.statusText, e.response.data);
                    let message = e.response.data;
                    if (message?.length)
                        throw new Error(`HTTP ${e.response.status}: ${message}`);
                }
                else
                    console.error(`[%s] error %s`, name, e.stack);
                throw e;
            } finally {
                let dur = Date.now()-ts;
                console.error(`[%s] tool finished in %sms`, name, dur);
            }
        };
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context: the requirement for a valid URL, the cache lookup behavior, and reliability advantage over scraping. However, it doesn't cover critical aspects like error handling, rate limits, authentication needs, or what 'structured data' entails in the output, leaving gaps for a mutation/read tool.

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

Conciseness4/5

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

The description is appropriately sized with three sentences that are front-loaded with the core purpose. Each sentence adds value: purpose, parameter requirement, and behavioral insight. It avoids redundancy, though minor trimming (e.g., 'Quickly' is subjective) could make it a 5.

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 tool's complexity (data extraction), no annotations, no output schema, and low schema coverage, the description is moderately complete. It covers purpose, parameter semantics, and a key behavioral trait (cache reliability), but lacks details on output structure, error cases, or integration with siblings, making it adequate but with clear gaps.

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?

The description adds meaningful semantics for the single parameter: 'Requires a valid booking hotel listing URL.' This clarifies that the 'url' parameter must be a booking hotel listing URL, not just any URI. With 0% schema description coverage and only 1 parameter, this compensation is effective, though it could specify URL format examples for a 5.

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: 'Quickly read structured booking hotel listings data.' It specifies the verb ('read'), resource ('structured booking hotel listings data'), and scope ('booking hotel listings'). However, it doesn't explicitly differentiate from siblings like 'web_data_zillow_properties_listing' or general scraping tools, which would require a 5.

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?

The description provides some usage context: 'Requires a valid booking hotel listing URL' and 'This can be a cache lookup, so it can be more reliable than scraping.' This implies when to use it (for booking hotel URLs) and hints at an advantage over scraping tools, but it doesn't explicitly name alternatives like 'scrape_as_html' or specify when-not-to-use scenarios, falling short of a 4 or 5.

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/dsouza-anush/brightdata-mcp-heroku'

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