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

The description adds significant context beyond the annotations: it's a real payment ('sends real USDC'), has a max amount ($5), is gasless (Coal pays gas), automatically uses the X-Coal-Agent-Key header, and returns an on-chain tx hash. It also implies external side effects aligned with `openWorldHint` and `destructiveHint`. No contradiction with annotations.

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 longer than typical but every sentence earns its place, covering purpose, usage trigger, gas details, key handling, limits, and follow-up. It's front-loaded with the core action and then supplies necessary constraints. Slight verbosity keeps it from a 5, but it remains efficiently structured.

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?

Despite no output schema, the description states the return value (tx hash) and the necessary follow-up (`download_product`). It covers prerequisites (key from header), limits (max $5), and the real-world nature of the transaction. For a payment tool with annotations and a clear schema, this is complete enough for an agent to operate effectively.

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?

The input schema already has 100% coverage, so baseline is 3. However, the description adds crucial disambiguation: `to` is the merchant payout address, not merchantId, and clarifies that `amount` is capped at $5. It also explains `agentPrivateKey` is optional if the header is set, which is not immediately obvious from the schema alone.

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 specifies the exact action ('Send USDC on Base to any merchant payout address') and explicitly distinguishes the target field (`payoutAddress`, NOT `merchantId`), making it clear this tool handles real payments. It differentiates from sibling tools like `discover_merchants` by saying the address comes from that tool's output, so the agent knows exactly when to use this one.

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?

Explicit usage trigger is given: 'Use this whenever the user has confirmed they want to buy, purchase, pay, or send money for something.' It also provides a post-condition ('After this succeeds for a digital product, immediately call download_product with the returned tx hash') and clarifies key handling ('no need to ask the user for a key'), giving clear when-to-use and follow-up guidance.

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