Skip to main content
Glama
james-webdev

TrustRails MCP Server

by james-webdev

search_products

Search and compare prices for 26,000+ UK electronics products across multiple retailers. Filter by brand, category, and price range to find the best deals.

Instructions

Search 26,000+ deduplicated UK electronics products across multiple retailers with price comparison. Returns summary data: title, brand, price, availability, category, purchase link, and offer_count. When offer_count > 1, the product is available from multiple retailers — call get_product to see all offers. Specs are minimal — for full technical specifications, call get_product with the product ID. Covers: Laptops, Desktops, Phones, Tablets, Headphones, Monitors, TVs, Cameras, Keyboards, Mice, Speakers, Gaming, Wearables, Printers, Networking, Storage, Audio, Drones, Cables & Chargers. All prices in GBP. IMPORTANT RULES: 1) Decompose the user's request: extract brand → brand filter, category → category filter, price → price filters. What remains is the query. Example: 'Sony headphones under £200' → brand='Sony', category='Headphones', max_price=200, query omitted. Example: 'MacBook Neo' → brand='Apple', category='Laptops', query='neo'. Example: 'Samsung QLED TV' → brand='Samsung', category='TVs', query='qled'. Example: 'Sony WH-1000XM5' → brand='Sony', category='Headphones', query='WH-1000XM5'. 2) DO NOT put brand names, product family names, full product name strings, or prices in the query — use filters. DO put differentiating identifiers: model lines, series, variants, technology descriptors, and model numbers (e.g. 'neo', 'ultra', 'oled', 'qled', 'WH-1000XM5', 's25 ultra'). Any product family name uniquely associated with a brand (e.g. MacBook→Apple, Galaxy→Samsung, ThinkPad→Lenovo) is already implied by brand+category — never put it in query. BAD: query='macbook neo' → GOOD: brand='Apple', category='Laptops', query='neo'. 3) If brand + category alone fully describe what the user wants, omit the query entirely — fewer query words gives cleaner results. 4) Always set lite=true to reduce payload size. 5) If 0 results, try a shorter/broader query or drop filters. 6) Use get_product for full specs — do not rely on search results for detailed attributes. AI USAGE PROTOCOL: For simple browsing, search with lite=true is sufficient. For spec-based queries (wattage, ports, RAM, screen size, weight, etc.), ALWAYS search first, then call get_product on the top 3-5 results and validate constraints against the full specs before recommending. Do not assume technical specs from titles alone. If specs are missing, state that explicitly. STOCK AVAILABILITY: When a product is availability: out_of_stock, do not recommend it as a purchase. Instead mention it as a notable alternative — especially if it offers a meaningful price advantage — and suggest the user check back. Example: 'This model is £X cheaper at [retailer] but currently out of stock — worth checking back if you're not in a rush.' Never silently omit out-of-stock results; surface them transparently.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoRefinement terms after brand and category are extracted. Use for model lines, series names, variants, or model numbers (e.g. 'neo', 'ultra', 'oled', 'qled', 'WH-1000XM5'). DO NOT include brand names, product family names, or prices — use filters. Omit entirely if brand + category fully describe what the user wants.
min_priceNoMinimum price in GBP. Use this instead of putting prices in the query.
max_priceNoMaximum price in GBP. Use this instead of putting prices in the query.
brandNoFilter by brand name (exact match, case-insensitive). Use this instead of putting brand names in the query. Examples: Apple, Samsung, Sony, HP, Dell, Lenovo, Anker, Bose, LG
categoryNoFilter by product category. Use ONLY these exact values: Laptops, Desktops, Tablets, Phones, TVs, Monitors, Headphones, Speakers, Cameras, Keyboards, Mice, Printers, Networking, Storage, Gaming, Wearables, Drones, Audio, Cables & Chargers. NOTE: 'Smartphones' is not valid — use 'Phones'. 'Televisions' is not valid — use 'TVs'. For TVs, use query: 'smart TV' — it returns far more results than 'TV' alone. Avoid query: 'television'.
liteNoReturn trimmed product objects with only essential fields (id, title, brand, price, availability, image_url, purchase_url). Always set to true unless the user specifically needs full product objects.
limitNoMaximum number of products to return (default 50, max 100)
sortNoSort order: 'relevance' (default), 'price_asc' (cheapest first), 'price_desc' (most expensive first). Use 'price_asc' when comparing prices.
Behavior5/5

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

No annotations are provided, so the description fully compensates by detailing that the tool returns summary data, that offer_count>1 indicates multiple retailers, that specs are minimal, and how out-of-stock items should be surfaced. It also notes all prices are in GBP.

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 well-structured with sections (important rules, AI usage protocol, stock availability) and front-loaded with the main purpose. However, it is somewhat verbose and contains some repetition in the query rules.

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 absence of an output schema, the description adequately explains the return fields (title, brand, price, availability, etc.) and covers all parameters, usage guidelines, edge cases like zero results and out-of-stock items. It is thorough for a search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema coverage is 100%, the description adds significant value by explaining the decomposition logic for query, brand, and category parameters, listing valid category values, and specifying when to omit the query. It goes beyond the schema descriptions.

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 tool's main function: 'Search 26,000+ deduplicated UK electronics products across multiple retailers with price comparison.' It lists covered categories and distinguishes itself from sibling tool get_product by noting that this tool provides summary data while get_product offers full specs.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool versus get_product, how to decompose user requests into filters and query, when to omit the query, and important rules like setting lite=true. It also addresses zero-result handling and AI usage protocol.

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/james-webdev/trustrails-mcp-server'

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