Skip to main content
Glama

BRAINIAC E-commerce Catalog Intelligence

Normalize product records

ecommerce-catalog_product-normalize

Read a brainiac-catalog-v1 or Google Merchant subset feed and standardize sku, title, category, price, availability, and GTIN. A dollar sign is not treated as USD, and missing materials or dimensions are not filled in. Price $0.04 USDC. POST /api/v1/ecommerce-catalog/product-normalize. Unpaid calls return 402 and do not run.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ecommerce-catalog_product-normalize"
  }
}

Input Schema

NameRequiredDescriptionDefault
csvNo
fileNo
jsonNo
productsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the endpoint, a fixed $0.04 USDC price, and that unpaid calls return 402 without executing. It also pins down two non-obvious normalization policies (no currency inference from '$', no synthesis of missing materials/dimensions). Still missing is whether the call is a pure transform returning records or a persistent write, and what happens to records that fail normalization.

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?

Four short sentences, front-loaded with the transform behavior before commercial and transport details. Every sentence carries information, though the currency clause reads tersely and could be clearer as a plain policy statement.

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 tool with four input modes, a 500-item nested product schema, no output schema, and no annotations, the behavioral side is reasonably covered but the input contract is not. An agent still cannot tell how to choose between csv, json, file, and products, or what the response looks like.

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

Parameters2/5

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

Schema description coverage is 0% and there are four input parameters (csv, file, json, products) plus a deeply nested product object with ~30 fields. The description lists normalized field names but never explains which parameter accepts which input, that at least one is required (all are optional in the schema), or that the four inputs are alternative carriers rather than additive. This is the largest gap in the definition.

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?

States a specific verb and resource ('standardize sku, title, category, price, availability, and GTIN' from a catalog feed), plus the two accepted feed dialects. That is far more precise than a name restatement, but it never positions itself against siblings like product-feed-validate or product-attribute-extract, so the agent must infer the boundary from names alone.

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?

Usage is implied by the input formats and the field list, and the 'not treated as USD' / 'not filled in' clauses usefully frame what the tool will not do. However, there is no explicit 'use this when' statement and no named alternative for validation versus normalization, so routing depends on inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources