Skip to main content
Glama

Call any verified data API through BitTuitive (paid: L402 sats or x402 USDC)

route_call

BitTuitive pays a scoreboard-verified L402 API and returns its data plus routing metadata — use this when the data you need is on another paid API. Price: upstream price + routing fee (max(20%, 3 sats)); the 402 body shows the all-in amount. Sample (illustrative, not live): {"data":{"note":"The upstream API's JSON body is returned here unchanged."},"routing":{"routed_by":"BitTuitive L402 router","upstream":{"endpoint_id":"example-id","name":"Example L402 API","host":"example.com","data_type":"bitcoin","score":92},"paid_sats":15,"upstream_price_sats":10,"fee_sats":5,"fallback_used":false}} Pay: Call it, get HTTP 402 (or MCP payment_required) with a Lightning invoice and macaroon, pay the invoice, then retry with Authorization: L402 <macaroon>:<preimage>. Or pay the same all-in price in USDC on Base via x402 (see price_usd, price_breakdown_usd and accepts; routing fee included): sign accepts[0] with an x402 client and call route_call again with the SAME arguments plus the PaymentPayload in params._meta['x402/payment'] (or the base64 x402_payment argument). A routed call pays an upstream API, so your USDC is settled first; if every upstream fails you get a single-use credit token (pass it as credit). Give endpoint_id (from route_endpoints) OR data_type and/or q (best pick, with fallback). If status is 'running', repeat the same call with the same l402_credential, credit or x402_payment.

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": "route_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoKeywords for best-pick mode, e.g. 'air quality'.
creditNoCredit token from a failed routed call (instead of paying).
paramsNoOptional query parameters forwarded to the upstream API.
data_typeNo
endpoint_idNoScoreboard id from route_endpoints.
x402_paymentNoOptional x402 payment (USDC on Base): base64 PaymentPayload (v2, or v1 X-PAYMENT format) signed for accepts[0] of this tool's payment_required result. Alternative to params._meta['x402/payment']. Omit both to receive the payment requirements.
l402_credentialNoOptional L402 credential '<macaroon>:<preimage_hex>' (or 'L402 <macaroon>:<preimage>') from a paid invoice or an active subscription. Omit it to receive the Lightning invoice and macaroon.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / x402_payment
      Added value: +{
      +  "description": "Optional x402 payment (USDC on Base): base64 PaymentPayload (v2, or v1 X-PAYMENT format) signed for accepts[0] of this tool's payment_required result. Alternative to params._meta['x402/payment']. Omit both to receive the payment requirements.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The annotations only say readOnlyHint=false and openWorldHint=true, but the description discloses far more: the fee formula max(20%, 3 sats), the all-in pricing shown in the 402 body, settlement ordering ('USDC is settled first'), the single-use credit issued if every upstream fails, and the fact that routing metadata is included in the response. This is the kind of paid-operation context that structured fields cannot 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?

Purpose is front-loaded in the first sentence and the remaining sentences are operational (pricing, payment flows, recovery). The inline illustrative JSON payload is bulky and only marginally load-bearing given there is no output schema to explain, which keeps it below top marks.

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?

For a seven-parameter tool spanning two payment rails, credit fallback, and asynchronous 'running' status with no output schema, the description covers pricing, payment mechanics, response shape, and error recovery. An agent has enough to invoke and recover without reading external docs.

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 already 86%, and the description still adds real meaning: it establishes that endpoint_id is interchangeable with data_type/q (best-pick with fallback), that x402_payment and params._meta['x402/payment'] are alternatives, that the same arguments must be reused on retry, and the accepted l402_credential format. The redundant sample payload keeps it from a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource: 'BitTuitive pays a scoreboard-verified L402 API and returns its data plus routing metadata,' and adds the selecting condition 'use this when the data you need is on another paid API.' It also names route_endpoints as the source of endpoint_id. It stops short of distinguishing itself from other data-fetching siblings such as request_data or best_endpoint, whose overlap an agent must guess.

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

Usage Guidelines5/5

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

Explicitly states when to use it (data lives on another paid API), how to invoke it in best-pick vs direct mode, the two payment paths (L402 Lightning, x402 USDC on Base), what to do on HTTP 402/MCP payment_required, how to reuse a returned credential or credit token, and the retry rule when status is 'running'.

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.

Resources