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

Annotations already mark this as a non-read-only, non-idempotent, non-destructive open-world operation. The description adds meaning beyond that: it is free, it produces a human-facing Checkout link, and crucially it discloses top-up behavior ('with a key already on the request it tops that key up instead'), which explains the non-idempotent semantics. Return/expiry details of the key are left to the output schema.

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?

Three tight sentences plus a compact example, with the primary purpose front-loaded and constraints following in logical order. No filler sentences.

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?

With a single fully documented parameter, existing annotations, and an output schema covering return values, the description supplies everything an agent needs: why to call, when to call, when not to, and the top-up edge case.

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?

Schema coverage is 100% and the schema already documents amountUsd including the offered amounts (5, 10, 25). The description's example '{ "amountUsd": 10 }' adds a little practical guidance, but the schema does the heavy lifting, so the baseline of 3 applies.

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 names a precise verb and resource: 'Mints a prepaid key and a Checkout link for a human to pay by card.' It further explains the downstream effect (later paid calls debited from balance), which cleanly distinguishes it from siblings like get_balance or start_comparison.

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?

It gives explicit trigger ('when a call was refused for payment and your human prefers a card to a wallet'), an alternate path ('use start_comparison with dryRun' to learn a price), and a negative condition ('do not call ... while the free allowance still covers the work'). This is a complete when/when-not/alternative triad.

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