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

Annotations carry destructiveHint=true and readOnlyHint=false, so the agent already knows operations may be destructive. The description adds value beyond the annotations by specifying the safe sequencing: obtain a refund-quote first, then pass its ID with an explicit confirmation constant. This is genuinely useful behavioral context for a destructive tool and does not contradict the 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?

Four tight sentences with zero filler, each covering a coherent action group. The most safety-critical guidance (balance non-preflight rule, refund confirmation sequence) is front-loaded. It is concise and well-organized, though a one-line opening stating the tool's general purpose would have made it slightly stronger.

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 10-parameter tool with 4 enums and no output schema, the description covers the main flows well: the refund pipeline, the checkout gating, and the balance/plans distinction. The portal, invoices, and trial-status actions are summarized in a single line, which is sufficient given they manage the existing account. Minor gaps remain around what each of those less-common actions returns, but nothing critical is missing for correct invocation.

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 every parameter already has a description, giving a baseline of 3. The description does reinforce the cross-parameter flow (refund-quote returns a quote ID that becomes refundQuoteId, paired with refundConfirmation), which adds slight connective meaning, but it does not introduce new format or syntax details beyond the schema. The baseline of 3 is appropriate.

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 never states an overarching purpose sentence, but each action's verb+resource is explicit: balance for inspecting credits, plans for comparing subscriptions, checkout, refund-quote, refund, portal, invoices, trial-status. The per-action clarity compensates for the missing single 'manages billing for the current account' statement, so it is clear but not maximally direct.

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?

This is exemplary routing guidance. It explicitly says when to use balance ('only when the user asks to inspect credits'), when not to ('do not preflight credit-consuming work'), when to use plans, and the exact sequencing for checkout ('only after the user chooses') and refund ('use refund-quote before refund, then pass its quote ID with explicit confirmation'). No inference is required.

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