Agent Weather

Base gas fees (paid: 0.001 RLUSD / 0.001 USDC on Base / 0.001 RLUSD on Base via x402)

base_gas_fees

Read-only

Paid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Pay per call, solves one question: What are Base EIP-1559 gas fee fields right now? Raw feeHistory/gasPrice readings with source and retrieved_at. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

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": "base_gas_fees"
  }
}

Input Schema

Name	Required	Description	Default
`payment_signature`	No	Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already flag readOnly, openWorld and non-idempotent, but the description adds the genuinely explanatory facts: every call costs 0.001 RLUSD/USDC, unpaid calls return isError with a fresh PaymentRequired invoiceId (explaining the non-idempotent hint), and unpaid attempts are free. It does not describe response size or limits, so it is not quite complete.

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?

Payment terms and the core question are front-loaded, and the retry mechanics follow logically. There is minor redundancy: the title already carries the pricing, and the first sentence repeats it, plus 'solves one question' is filler phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must convey return content, and it does ('Raw feeHistory/gasPrice readings with source and retrieved_at') as well as the full payment/error path. The exact shape of those readings is left unspecified, but for a paid single-purpose read tool this is close to sufficient.

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% for the single optional parameter, so the baseline is 3. The description goes further by explaining the two delivery paths for the signature — the _meta["x402/payment"] key versus the payment_signature argument — which the schema alone does not contrast.

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 names a specific resource and payload: 'Base EIP-1559 gas fee fields right now' returned as 'Raw feeHistory/gasPrice readings with source and retrieved_at'. That is concrete enough to separate it from siblings like base_block_tip, which do not return fee-history 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?

It explicitly frames the single question the tool answers and spells out the two-step invocation flow: first call unpaid to receive requirements, then retry with the signed payload. What is missing is any naming of alternatives (e.g. when to prefer base_block_tip or batch_readings), so it stops short of full when/when-not guidance.

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

All Agent Weather tools Inspect

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

Need Help?