Skip to main content
Glama

Link a card for agentic checkout

link_payment_method

Start linking a card for agentic checkout, with a guest-chosen spending cap. Returns a Stripe-hosted URL, hand this URL to the guest and have THEM open it and enter their own card there. Never ask the guest for their card number, expiry, or CVC in this conversation, and never pass card details as tool input; this app never accepts them. Requires session_token from verify_code.

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": {
      "session_token": "<session_token>",
      "cap_dollars": "<cap_dollars>"
    },
    "name": "link_payment_method"
  }
}

Input Schema

NameRequiredDescriptionDefault
cap_dollarsYesThe guest's own chosen spending cap in dollars, suggest $150 as a sane default, but the guest picks the real number on the Stripe page.
session_tokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover the generic safety profile (not read-only, open-world, not idempotent); the description adds what actually happens — it initiates a link flow, returns a hosted URL, and the guest completes card entry out-of-band. It also states a hard prohibition on accepting card data, which is behavioral context the 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 purpose and return value, then the safety constraints. The card-data prohibition is stated twice ('never ask the guest...' and 'never pass card details as tool input'), a mild redundancy justified by the high-stakes nature but still slightly wasteful.

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?

With no output schema, the description carries the return contract and does so explicitly (Stripe-hosted URL plus who opens it). Prerequisite, safety boundary, and next step are all present, so nothing needed to call this correctly is missing.

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 50% (session_token undocumented in schema), and the description compensates by naming the token's source (verify_code). It also characterizes cap_dollars as the guest's own chosen cap rather than an operator-set value, adding meaning beyond the schema's $150 suggestion.

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?

States a specific verb and resource ('Start linking a card for agentic checkout') plus the scoping detail of a guest-chosen spending cap, and immediately names the return artifact (a Stripe-hosted URL). An agent can distinguish this from reserve_and_pay or get_payment_method without opening any 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?

Gives an explicit upstream dependency ('Requires session_token from verify_code') and a precise next action ('hand this URL to the guest and have THEM open it'), which effectively defines the usage context. It stops short of naming an alternative tool or stating when-not-to-use, which keeps it off 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.

Resources