Skip to main content
Glama

agtmart sandbox store and agent survey

Check out (sandbox: test card, USDC or USDT)

checkout

Place a SANDBOX order: nothing ships and no money moves. payment.method is 'card', 'usdc' or 'usdt'. card: only test cards work (4242424242424242 succeeds, 4000000000000002 declines; any future expiry, any 3-digit cvc). usdc (networks base, ethereum, solana, polygon) or usdt (ethereum, tron, solana): returns a simulated payment_request with the amount in token units (6 decimals), a SANDBOX pay_to that is not a real address, and an expiry; then call confirm_crypto_payment with a fake tx hash. Never send real funds or a real card.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "cart_id": "<cart_id>",
      "payment": "<payment>"
    },
    "name": "checkout"
  }
}

Input Schema

NameRequiredDescriptionDefault
cart_idYes
paymentYes
shippingNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations (which only say non-read-only, non-destructive, non-idempotent, non-open-world), the description discloses that no money moves, that specific test card numbers succeed or decline, and that the crypto path returns a simulated payment_request with 6-decimal token amounts, a non-real pay_to, and an expiry. The safety constraint "never send real funds or a real card" is exactly the kind of context annotations cannot express.

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?

Front-loaded with the sandbox caveat, then ordered by payment method, which mirrors the decision the agent must make. It is dense but nearly every sentence carries operational detail; the closing warning is slightly redundant with the opening line.

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?

For a mutating, nested-payload tool with no output schema, the description covers the payment branch thoroughly including the downstream step. The remaining gap is cart_id provenance and what shipping means when nothing ships, which an agent must guess.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden, and it does explain payment.method values, the valid networks per method, and card field expectations (any future expiry, any 3-digit cvc). However cart_id is never explained — neither its meaning nor where it comes from — and the shipping object's behavior in a sandbox order is left unaddressed, so compensation is only partial for a nested-object schema.

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?

"Place a SANDBOX order: nothing ships and no money moves" gives a specific verb and resource plus the scope qualifier that separates it from a real checkout. It also names the follow-on sibling confirm_crypto_payment, so an agent can place it in the flow without opening another schema.

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?

Strong conditional guidance: which payment.method values exist, which networks pair with usdc vs usdt, and exactly when to escalate to confirm_crypto_payment with a fake tx hash. What is missing is any stated precondition on cart_id (e.g. that the cart must exist from add_to_cart) or explicit exclusion guidance.

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