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

Annotations declare a non-read-only, open-world, non-idempotent write, and the description adds genuinely new context: the call does not itself complete payment, it returns a checkout URL that the agent must surface to the user, implying repeated calls create new sessions. It omits auth/permission requirements and any rate limits.

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?

Two tight sentences, front-loaded with the action, then the critical behavioral detail (returns a URL) and the constraint. No filler or redundancy.

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?

For a single-parameter tool with no output schema, the description covers what an agent needs: the mutation, the indirect completion path, and the amount bound. The return value is explained even though no output schema exists.

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 description coverage is 100%, with amount_usd's type, minimum, maximum and examples already documented in the schema. The description's 'Minimum $1' merely repeats the schema's stated minimum, adding no new semantics. Baseline 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?

States a specific verb and resource ('Add credits to your account') and immediately characterizes the outcome as a Stripe checkout URL, which is unmistakably distinct from the read-only siblings credits_balance and credits_usage. It never names a sibling explicitly, so it stops short of full differentiation.

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?

The description implies the flow ('share it with the user to complete payment'), which tells the agent this is a hand-off step rather than a completed transaction. It gives no explicit when-to-use/when-not guidance or contrast with alternatives such as subscription_manage or invoice_list.

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