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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description adds the material fact that real money is captured immediately and that a Shopify order is created as a side effect — behaviorally richer than the annotation flags. It stops short of describing failure handling (e.g., what happens if the charge is declined) or whether retries are safe.

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 sentences, front-loaded with "WRITE: CHARGES ... NOW" so the riskiest fact appears first, then the guard condition, then the endpoint. 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?

For a destructive money-moving tool with full schema coverage and no output schema, the description covers intent gating and side effects adequately. Minor gaps remain around post-call semantics (what the resulting order/charge looks like, decline handling) but nothing an agent needs before invoking it.

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%; both subscription_id and billing_attempt_id are documented in-schema, including the pointer to billing_attempts[].id from sealsubscriptions_get_subscription. The description adds only the framing that the attempt may be a failed or upcoming one, 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?

States a precise verb and effect: charges the customer's payment method now for one specific billing attempt and creates a Shopify order, with the concrete example of a failed or upcoming attempt. It does not, however, distinguish itself from the sibling sealsubscriptions_create_charge_now, which an agent could easily confuse with this tool.

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?

"Only call it when the user clearly asked for that charge" is an explicit gating condition that tells the agent to require clear user intent before an irreversible charge. It stops short of naming the alternative to use when creating a charge outside a billing attempt, so the sibling routing is left implicit.

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