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

Beyond the readOnlyHint=false annotation, the description discloses important workflow behavior: balance must not be used for preflight checks, checkout requires prior user choice, and refunds require a quote ID plus explicit confirmation. It does not fully describe side effects of portal actions or subscription cancellation flows, but the provided behavioral guidance is substantial and does not contradict annotations.

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?

Five tightly packed sentences, each conveying a distinct operational rule with no filler. The most important guidance about balance is front-loaded, and the final sentence efficiently summarizes the account-management actions.

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 an 8-parameter tool with no output schema, the description provides strong action routing and ordering context. It leaves some gaps, such as when to use each flow value (subscription_update_confirm vs subscription_cancel vs subscription_stop_cancel) and what responses look like, but the core invocation decisions are well covered.

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%, so the baseline is 3, and the description adds value by connecting parameters to workflow steps: refundQuoteId is tied to the refund-quote action, refundConfirmation is the explicit confirmation, priceLookupKey is the plan returned by plans, and trialCode is for checkout. Some parameters like surface and flow are only lightly contextualized, but the description meaningfully complements the schema.

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 specific actions and resources: 'inspect credits', 'compare live subscriptions', 'create checkout', 'refund', and 'manage the existing account'. It clearly distinguishes the billing actions from one another, and the sibling tool list contains no overlapping billing tool, so an agent can tell when this tool is relevant.

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 when-to-use rules: balance 'only when the user asks to inspect credits', plans 'before recommending a purchase', checkout 'only after the user chooses', and refund-quote 'before refund'. It also provides an explicit exclusion with 'do not preflight credit-consuming work' and names the sequence and confirmation requirements.

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