Skip to main content
Glama

Coal — Payments for AI agents

by io.github.emmanuel39hanks

Create Checkout Session

create_checkout

Create a Coal checkout session to pay for a product or amount. Settles in USDC on Base (~2s). Returns a checkout URL. Needs a Coal API key — set once via Claude config header X-Coal-Api-Key:YOUR_KEY, or pass per-call as coalApiKey. Get one at https://usecoal.xyz/console/keys.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
amountYesPayment amount in USD
productIdNoOptional Coal product ID
coalApiKeyNoYour Coal API key (optional if X-Coal-Api-Key header is set)
descriptionNoPayment description
productNameNoProduct name for the checkout page

TDQS

A4.4/5.0
Behavior5/5

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

The description discloses API key requirements (header or per-call), settlement network and time (~2s), and the fact that it returns a checkout URL. These traits go beyond the annotations, which only indicate read-only/idempotent/destructive hints, providing critical operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three focused sentences covering purpose, behavior, and authentication. No redundant content, each sentence adds value, and key information is front-loaded.

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?

Given the tool's complexity (5 params, no output schema), the description covers purpose, output, settlement details, and API key setup. It lacks edge-case guidance (e.g., product vs amount precedence) but is generally complete for an AI agent to invoke correctly.

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?

The input schema already provides descriptions for all 5 parameters (100% coverage), so the description adds little parameter-specific detail. It does clarify that payment can be for a product or amount, aligning with productId and amount, but this is marginal. Baseline 3 is appropriate.

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?

The description clearly states 'Create a Coal checkout session to pay for a product or amount,' specifying the verb and resource. It distinguishes from siblings like pay_merchant and get_checkout_status by focusing on session creation and returning a checkout URL.

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?

The description provides clear context: it is for initiating a checkout, settles in USDC on Base, and requires an API key. However, it does not explicitly mention when to use this tool over alternatives like pay_merchant, so it slightly lacks explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Coal — Payments for AI agents toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation3/5

Several tools overlap in the product discovery and payment status domains. discover_merchants, search_products, and get_merchant_profile all relate to finding products/merchants, though descriptions clarify intended use. Similarly, check_paywall, get_checkout_status, and verify_receipt all deal with payment status/verification, creating potential agent confusion.

Naming Consistency4/5

Most tools follow a consistent lowercase verb_noun pattern (check_paywall, create_checkout, download_product, get_0g_health, etc.). The one outlier is agent_wallet_status, which is a noun phrase instead of verb-first, but it still uses underscores and fits thematically.

Tool Count4/5

13 tools is within the ideal range and the server covers payments, product discovery, and verification. A few tools like get_0g_health and setup_instructions feel tangential to the core payment flow, making the set slightly heavier than necessary but still reasonable.

Completeness4/5

The payment lifecycle is well covered: discover/search products, pay via checkout or direct merchant payment, download digital goods, and verify receipts. Minor gaps exist such as no explicit refund or transaction history tool, but agents can work around these by using existing verification and wallet status tools.

Resources