CPG product data + shop prices by barcode or name. Open Food Facts + Open Prices. Ed25519 attested. [x402 paid: GET /api/x402/cpg-product-intel-json price $0.004 on Base]
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Product name search | |
| barcode | No | EAN/UPC barcode |
Changes observed during successful MCP inspections.
Input schema / properties / barcode / descriptionPrevious value: -"GTIN/EAN/UPC barcode, e.g. \"5449000000996\". Primary."New value: +"EAN/UPC barcode"Input schema / properties / domainRemoved value: -{
- "description": "food|beauty|products|petfood (default auto with fallback).",
- "type": "string"
-}Input schema / properties / name / descriptionPrevious value: -"Product name fallback for search (e.g. \"coca cola\")."New value: +"Product name search"Input schema / requiredAdded value: +[]Input schema / properties / domainAdded value: +{
+ "description": "food|beauty|products|petfood (default auto with fallback).",
+ "type": "string"
+}Input schema / properties / domainRemoved value: -{
- "description": "food|beauty|products|petfood (default auto with fallback).",
- "type": "string"
-}Input schema / properties / domainAdded value: +{
+ "description": "food|beauty|products|petfood (default auto with fallback).",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the whole behavioral burden and does disclose the important traits: response attestation (Ed25519) and that access is paid via x402 at $0.004 on Base, which tells the agent a payment flow is required. It does not mention rate limits, error/failure behavior, or latency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short telegraphic fragments, front-loaded with the resource and its identifiers. Dense and efficient, though the bracketed pricing fragment is slightly clunky and no fragment states an explicit action verb.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations exist, so the description must stand alone; it sketches the returned content (product data plus shop prices), its provenance, integrity guarantee, and cost/access model. It stops short of describing result shape or pagination, which is a minor gap for a two-input lookup tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so both parameters are already documented as 'Product name search' and 'EAN/UPC barcode'. The description adds only the generic 'barcode or name' framing and no format or precedence detail beyond the schema, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Names the resource (CPG product data plus shop prices) and the two lookup keys (barcode or name), and names the upstream sources (Open Food Facts, Open Prices). This is unmistakably distinct from every sibling, which are company/sanctions/web enrichment tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'by barcode or name' implies the two entry modes, but there is no when-to-use versus when-not guidance and no hint about which key to prefer or whether both can be combined. Usage is inferable but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.