Skip to main content
Glama
Sign In

Stablecoin Gateways

by com.stablecoingateways
OverviewDiscussionsAdmin

US Product Recalls CPSC FDA

product_recalls_us
Read-onlyIdempotent

Product recall check (US): has a product or brand been recalled? Searches CPSC consumer product recalls and FDA food, drug and medical device enforcement reports (openFDA) in one call; returns hazard or reason, remedy, date, FDA recall class and agency link. Use for product safety, e-commerce listing and procurement checks. Signed receipt. Price: $0.002 per call via x402 (USDC on Base or XRP on XRPL). The response includes a provenance block (sg-provenance/1): each fact carries its source, source URL, retrieval time and limits; evidence only, no score, rating or verdict. Example arguments: {"q":"stroller","source":"cpsc"}.

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": {
      "q": "<q>"
    },
    "name": "product_recalls_us"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesProduct or brand term
sourceNoWhich agencies; default all

Output Schema

NameRequiredDescriptionDefault
dataNoCPSC and FDA recall records: product, hazard or reason, remedy, date, class, agency link
receiptNoEd25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt. New receipts carry a signed `evidence` object: service_version, data_timestamp, validation, terms_version, terms_hash, provenance_hash.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / data / properties / provenance
      Added value: +{
+  "description": "The response includes a `provenance` block (sg-provenance/1): each fact carries its source, source URL, retrieval time and limits; evidence only, no score, rating or verdict."
+}
  2. Changed1 schema field changed
    • changedOutput schema / properties / receipt / description
      Previous value: -"Ed25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt"New value: +"Ed25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt. New receipts carry a signed `evidence` object: service_version, data_timestamp, validation, terms_version, terms_hash, provenance_hash."
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "Paid result: { data, receipt }. Unpaid calls return an x402 PaymentRequired object instead (isError: true).",
+  "properties": {
+    "data": {
+      "description": "CPSC and FDA recall records: product, hazard or reason, remedy, date, class, agency link",
+      "properties": {
+        "cpsc": {},
+        "fda": {},
+        "partial_errors": {},
+        "query": {},
+        "retrieved_at": {},
+        "source": {},
+        "sources": {}
+      }
+    },
+    "receipt": {
+      "description": "Ed25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt"
+    }
+  },
+  "type": "object"
+}
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description adds value well beyond them: it discloses what the response contains (hazard/reason, remedy, date, FDA recall class, agency link), a provenance block with per-fact source/URL/retrieval time/limits, a signed receipt, and the pricing model ($0.002/call via x402 USDC on Base or XRP on XRPL). Cost and provenance semantics are exactly the kind of information an agent cannot get from annotations.

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?

Front-loaded with the core question and sources in the first sentence, then usage, then response shape, then commercial/trust metadata. Every sentence carries distinct information, though the provenance and pricing clauses are dense enough that the description runs long for a two-parameter tool.

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?

Although an output schema exists, the description still characterizes the return payload (specific fields, provenance structure, signed receipt), covers payment prerequisites, and provides a worked example. For a paid, open-world tool an agent must decide whether to spend budget on, nothing material is missing.

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?

Schema coverage is 100% and both parameters are documented (q = product or brand term; source enum all/cpsc/fda), so the baseline is 3. The description supplements this with a concrete example call showing q and source in combination, which adds practical value beyond the schema. It does not explain the 2-80 character bounds or the default behavior for source, keeping it from a 5.

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?

States a specific verb and resource ('product recall check', 'has a product or brand been recalled?') plus the exact two data sources (CPSC consumer product recalls and FDA openFDA enforcement reports). This is clearly distinguishable from every sibling tool (sanctions_screen, merchant_check, domain_facts, etc.), none of which touch recall data.

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

Usage Guidelines4/5

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

Names concrete use contexts: product safety, e-commerce listing checks, procurement checks. There are no true alternatives among the siblings, so the absence of explicit exclusions is a minor gap rather than a routing failure. The 'evidence only, no score, rating or verdict' line also implicitly tells the agent not to use it as a pass/fail screening verdict.

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

All Stablecoin Gateways toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources