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

Annotations already indicate idempotentHint and non-readOnly, but the description adds valuable behavior beyond annotations: it states that the tool does not actually pay, and instructs reusing the idempotency key after timeouts. This gives practical safety context not present in the structured fields. It doesn't discuss authentication or side effects in detail, but the key behavioral points are covered.

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 compact and front-loaded. The first sentence states the core action and a crucial caveat, followed by two short operational instructions and one routing instruction. Every sentence earns its place with no filler.

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 tool with only two parameters)Skip. The description covers the purpose, the non-payment caveat, the idempotency behavior, and the relevant sibling alternative. An output schema exists, so return-value details are not required. It could be slightly more complete by explicitly mapping pack_id to credit amounts, but overall the agent has enough context to call it correctly.

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 0%, so the description must compensate, but it does not explain what pack_id represents beyond implication from 'top up', nor does it describe how idempotency_key should be generated or used beyond the timeout hint. The enum values and pattern in the schema carry most of the meaning; the description adds little semantic value for the parameters.

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 specific verb and resource: 'Create a human Stripe checkout to top up this connected account'. It immediately clarifies a common misconception with 'does not pay', and distinguishes itself from prepare_session_checkout by name. This is unambiguous and well differentiated from siblings.

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 gives explicit operational guidance: present price and checkout_url, reuse the same idempotency key after timeouts, and use prepare_session_checkout instead for first signup-free purchases. This clearly tells the agent when and how to use the tool versus its alternative.

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