Skip to main content
Glama
@caelaralabs/mcp

@caelaralabs/mcp

caelara_ecom_product_intel_composite

Extract product page intelligence from a URL: parse JSON-LD, validate GTINs, normalize SKUs, score review sentiment, detect ad pixels, and analyze price signals.

Instructions

[E-Commerce Intelligence] Product page intelligence: JSON-LD product, GTIN validation, SKU normalization, review sentiment, ad pixels and price signals Measured p50 11 ms, p95 15 ms (2026-11-21, benchmarks.caelaralabs.com). Calls https://ecom.caelaralabs.com.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "caelara_ecom_product_intel_composite"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesProduct page URL

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden, and it does provide useful operational context: measured p50/p95 latency and the external endpoint being called. However, it never states that the call is read-only/non-mutating, what happens when the page lacks JSON-LD or GTIN, or whether failures are per-signal partial or all-or-nothing. Those are material gaps for a network-scraping tool with zero annotation coverage.

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 capability list is front-loaded and dense, with no filler prose, and the latency/endpoint line is compact. The first sentence is a run-on noun phrase with no verb, which slightly hurts scannability, but overall the text is efficiently sized for the amount of information conveyed.

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?

For a one-parameter composite with no output schema and no annotations, the description covers what categories of data come back and how fast, which is enough to decide to call it. What is missing is the shape/format of the response (single JSON object of fields vs. separate sections) and failure semantics, which the absence of an output schema makes more important to state in prose.

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 tool takes a single required parameter whose purpose ('Product page URL') is fully documented in the schema, so the baseline is already high. The description adds marginal value by implying the URL should point at a product page whose embedded signals are parsed. No further syntax or format clarification is needed for a lone URL argument.

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 names a specific resource (product page) and enumerates the exact signals extracted: JSON-LD product data, GTIN validation, SKU normalization, review sentiment, ad pixels, and price signals. That makes the tool's output scope concrete and distinguishes it as the bundled/composite variant of the single-purpose siblings. It loses a point because there is no verb-led statement of what it actually does (extract/analyze) and no explicit contrast with the individual parser tools.

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?

There is no guidance on when to choose this composite over the single-purpose siblings (jsonld_product_parser, gtin_upc_validator, sku_normalizer, review_sentiment_parser, ad_pixel_detector), even though those clearly overlap. No prerequisites, no input expectations (e.g. that the URL must be a product detail page rather than a category page), and no exclusions are stated. An agent must infer the usage pattern from the name alone.

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

Deploy Server

Other Tools