create_onramp_sessionUse this when a US user wants to buy USDC on Base with a card / Apple Pay / Google Pay. Returns a payment link a HUMAN must physically tap (fiat legs cannot be programmatically triggered); a human is notified. US-only guest checkout, <= $500/week.
| Name | Required | Description | Default |
|---|---|---|---|
| geo | No | ||
| amountUsd | Yes | ||
| destinationAddress | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses key behavioral traits beyond the openWorldHint annotation: a human must physically tap the payment link, fiat legs cannot be programmatically triggered, and a human is notified. This is critical for an agent deciding how to invoke the tool.
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?
Two sentences with no waste. The first sentence front-loads the core purpose and usage, and the second adds critical behavioral transparency. Every sentence earns its place.
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?
Given the simple schema (3 params, no output schema) and annotations, the description covers the main behavioral and usage aspects. Lacks details on response format or error handling, but is sufficient for basic invocation.
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?
With 0% schema description coverage, the description must compensate but only provides high-level context (US-only hints at geo='US'). It doesn't specify allowed values or formats for amountUsd or destinationAddress, leaving gaps for an agent.
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?
The description clearly specifies the action (create a session to buy USDC on Base), the target users (US users), and accepted payment methods (card/Apple Pay/Google Pay). It distinguishes from siblings like create_swap, which likely handles crypto-to-crypto swaps.
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 description explicitly states when to use: 'Use this when a US user wants to buy USDC on Base...' and includes constraints (US-only, <= $500/week). It implicitly guides away from non-US or higher amounts but doesn't explicitly name alternatives.
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.
Tools are mostly distinct, but create_swap and create_onramp_session both result in acquiring USDC on Base, and get_route_quote covers both fiat and crypto routes; minor potential for confusion.
All tools follow a consistent snake_case verb_noun pattern (check_swap, create_onramp_session, etc.), making the set predictable.
With 5 tools covering quoting, swapping, status checks, fiat onramp, and wallet creation, the count is well-scoped for the server's purpose.
The set covers quoting, swapping, fiat onramp, and wallet provisioning, but lacks offramp execution (crypto to fiat), cancellation, or token/chain discovery, leaving notable gaps.