get_fx_parallelStreet (parallel-market) rate — USD-NGN or USD-GHS. The rate a person actually transacts at, derived from live P2P order books, with the official rate and the spread. $0.05 USDC on Base. Returns the x402 URL to GET (402 → PAYMENT-SIGNATURE → delivery). Free to call this tool; payment happens on the URL.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | Yes | USD-NGN or USD-GHS (required) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full transparency burden and does so well: it discloses the $0.05 USDC cost, that the tool call itself is free, that payment happens on the returned URL, and the x402 flow (402 → PAYMENT-SIGNATURE → delivery). This is critical behavioral information beyond the schema.
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?
The description is reasonably compact and front-loaded, starting with the core purpose before adding cost and delivery mechanics. The first phrase repeats the title almost exactly, which is mildly redundant, but every subsequent sentence contributes unique, actionable information.
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?
The description explains the return value (an x402 URL), the payment requirement, and the follow-up flow, which is sufficient for a single-parameter tool with no output schema. It could go deeper on what the final delivered payload looks like, but the provided detail is enough to invoke correctly and understand the monetization model.
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 description coverage is 100%, so the schema already documents the 'pair' parameter with the acceptable values. The description adds context about what 'pair' means in this domain but mostly restates USD-NGN/USD-GHS rather than introducing new parameter-level guidance, so baseline 3 is correct.
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 identifies the resource (street/parallel-market FX rate for USD-NGN or USD-GHS), uses a specific 'get' verb, and distinguishes it from the official rate sibling by emphasizing 'the rate a person actually transacts at' and 'live P2P order books.' It also states exactly what is returned: an x402 URL.
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 'Street (parallel-market) rate' and the contrast with 'the official rate and the spread' gives clear context for when this tool is appropriate. It does not explicitly name alternatives such as get_fx_official, so it stops short of a 5, but the context is strong enough for a capable agent to select it.
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.
Most tools have clearly distinct targets: FX official vs parallel vs brief, carrier vs broker vs BASICs, name vs wallet sanctions, and insurance vs real-estate CE. The bundled tools (vet_load, get_fx_africa_brief, buy_shelf_pass) overlap with individual tools but their descriptions explicitly frame them as convenience packages or payment modes, reducing real misselection risk.
Every tool follows a consistent verb_noun snake_case pattern: buy_*, check_*, get_*, list_*, screen_sanctions_*, vet_load. There is no mixed casing or inconsistent verb styling across the set.
At 16 tools the set is slightly above the typical 3-15 range, but the server intentionally spans FX, freight, compliance, and the x402 purchase lifecycle, so most tools earn their place. The count feels a bit heavy but not bloated.
Core workflows are covered: shelf discovery, generic and pass-based purchasing, order status, pass balance, and the main FX, freight, OFAC, and Texas CE data shelves. Minor gaps such as cancellation/refund endpoints, non-US sanctions lists, or additional freight jurisdictions do not block primary agent workflows.