Skip to main content
Glama

agent-exec

Broadcast a USDC transfer you signed, with our gas (paid, x402)

relay_usdc

PAID: send USDC without gas: you sign an EIP-3009 transfer, we broadcast it on Base with our ETH. $0.0200 an order, at most $100. Unpaid, it returns the price; pay with x402 (USDC on Base, Solana, Polygon, Arbitrum, Avalanche, Sei or X Layer) in _meta['x402/payment'] and call again. Feedback: POST /feedback (free). Read daily; no individual reply.

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": "relay_usdc"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoRecipient of the USDC. Must differ from `from`.
fromNoThe USDC holder who signed. The signature must recover to exactly this address, e.g. 0x2222222222222222222222222222222222222222.
nonceNo32 bytes of hex, unused before: USDC itself rejects a reused one, so each order needs its own.
valueNoAtomic USDC (6 decimals) as a decimal string, 1..100000000 ($100 ceiling an order).
dryRunNoOptional. true: a dry run -- nothing is sent or changed, and the 200 answer (served:true, dryRun:true) says what this call would do with the rest of your body, or which fields are missing. A dry run is a paid call at this price. false or absent: the call runs.
signatureNoYour EIP-712 TransferWithAuthorization signature over chainId 8453, verifyingContract 0x833589fcd6edb6e08f4c7c32d4f71b54bda02913 (Base USDC). A refusal returns details.expected with the exact struct and domain.
validAfterNoUnix seconds, as a string; must already have passed.
validBeforeNoUnix seconds, as a string; at least 30s out, so the broadcast lands inside your window.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint false, destructiveHint false, openWorldHint false), it discloses the paid model ($0.0200/order, $100 cap), the unpaid price-discovery behavior, the accepted payment rails, and that a dryRun is itself billable. It also warns that nonces cannot be reused because USDC rejects them, which is critical operational context the annotations do not carry.

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?

Pricing and the paid/unpaid flow are front-loaded in the first sentence, which is exactly right for a payment-gated tool. The trailing feedback/response-cadence sentence is tangential to invocation but short enough not to bury the core instructions.

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 does useful work by indicating what an unpaid call returns (the price), what a dryRun returns (served:true, dryRun:true or missing fields), and that a signature refusal returns details.expected with the exact struct and domain. The success-path response (e.g., tx hash) is not described, which is the main remaining gap.

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 the schema already explains to/from/nonce/value/dryRun/signature/validAfter/validBefore thoroughly, so the baseline is 3. The description adds meaning not in the schema by specifying the payment channel (_meta['x402/payment']) and the valid paying chains, which is genuinely additive for invocation.

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?

"PAID: send USDC without gas: you sign an EIP-3009 transfer, we broadcast it on Base with our ETH" names the exact verb (broadcast/replay a signed authorization), the resource (USDC transfer), and the mechanism (EIP-3009 meta-transaction on Base). This is distinguishable from a permit-only sibling such as relay_permit because it states a transfer authorization is broadcast, not merely a signature/permit.

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 gives a clear operating workflow: call unpaid to get the price, pay with x402 in _meta['x402/payment'] on one of seven listed chains, then call again. It also states the per-order cost and ceiling, which sets expectations before calling. It stops short of explicit when-to-use-vs-alternative routing (e.g., relay_permit or pay_send), so it is not a 5.

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.