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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds substantial context beyond them: it states the tool never raises a protocol error, describes the error-return shape, and explains that retrying after correction is always safe. That is exactly the kind of behavioral detail an agent needs to handle failures and retries confidently.

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?

The description is compact and front-loaded: the core purpose comes first, followed by a compact worked example, usage routing, error contract, and retry safety. Every sentence carries information an agent needs, with 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?

The tool is a simple read-only calculation with an output schema already present, so the description does not need to explain return values in detail. It still covers the worked example, error behavior, usage boundaries, and idempotency, leaving nothing critical for an agent to infer before calling 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 description coverage is 100%, so the schema already documents every parameter. The description still adds value by walking through a concrete input/output example that maps amount_per_period, days_used, and days_in_period to the returned prorated_charge and prorated_refund. It does not explain refund_mode in the description, which keeps it from a 5.

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: 'Compute a prorated charge or refund for a partial billing period.' This is precise enough to distinguish the tool from siblings like installment_plan, which is explicitly named as the wrong tool for scheduled payments.

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?

It gives an explicit when-to-use condition ('a plan starts, ends, or changes mid-period') and an explicit when-not-to-use alternative ('Not for splitting a full amount into scheduled payments (installment_plan)'). The routing decision is fully specified.

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