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

Annotations already signal read-only, idempotent, and non-destructive behavior, so the description's burden is lower. It adds valuable behavioral detail: the ~18s long-poll timing, the exact status enum, the semantics of `grantApplied`, and the webhook timing caveat ('has or is about to apply the grant'). This is consistent with the annotations and goes well beyond them.

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 sentences, each earning its place: the first states what the tool does and returns, the second gives the open-status instruction, and the third explains the grantApplied flow. Key information is front-loaded and there is 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?

Because there is no output schema, the description correctly takes responsibility for explaining the return shape and the meaning of key fields. It also covers the two follow-up actions an agent must take depending on the result. With one well-documented parameter and rich annotations, nothing essential is missing for safe invocation and correct follow-through.

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 explains that `sessionId` is a Checkout Session id (`cs_…`) from `checkout`. The tool description does not add any additional meaning for the parameter beyond what the schema provides, 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 opens with a specific verb and resource: 'Long-poll a Checkout Session from `checkout`'. It also defines the tool's output (payment status with open/complete/expired), which distinguishes it from sibling polling tools like poll_approval and poll_pairing. The reference to `lookup` as a follow-up further clarifies its role in the payment flow.

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 concrete conditional usage instructions: if status is 'open', tell the user to finish paying and call poll_checkout again; if 'grantApplied' is true, call `lookup` to confirm. It names `lookup` as the next step, but does not explicitly state when to use poll_checkout versus other related sibling tools beyond the checkout context. This is strong but not a full when/when-not guide.

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