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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description is not required to restate them. It still adds real context beyond structured data: credit never expires, and the balance includes amounts held by an in-flight session, which explains why spendable_seconds may differ from the raw balance.

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 short sentences, front-loaded with the core purpose and the enumerated fields, then the business rule, then the escalation path. No restatement of the title and 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?

An output schema exists, so return values need not be fully specified, yet the description still names the key fields an agent should inspect. Combined with the never-expires rule and the get_mac_checkout fallback, an agent has everything needed to call and act on this tool.

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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly spends no space on argument semantics and instead documents the shape of the result.

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+resource ('Read the prepaid Mac credit balance') and enumerates the concrete payload fields: spendable dollars, spendable_seconds, amounts held by a running session, pricing, and recent purchases. It also names a sibling (get_mac_checkout), so an agent can distinguish it without opening another schema.

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?

Gives a clear conditional: if spendable_seconds is below what the task needs, call get_mac_checkout. That is genuine routing guidance, though it doesn't contrast against nearby read tools like get_billing_status or get_mac_session, so the 'when not to use this' dimension is only partially covered.

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