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

With no annotations provided, the description carries the full burden of disclosing side effects and behavior. It reveals the tool is paid, modifies credit balance, imposes financial limits, and clears read-only grace—each a significant behavioral trait beyond the obvious 'top-up'. It also explains the two-step payment flow (call without payment_b64, then retry with it), which is essential for correct invocation. It does not cover error states or what happens on failed payment, but the disclosed information is substantial and accurate.

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 three sentences and front-loads the critical 'PAID' flag, immediately setting expectations. It packs a lot of information—payment flow, rate, limits, and effects—without redundancy. The only minor inefficiency is the lengthy first sentence, but it is dense and necessary. Overall, it is well-structured for an agent to quickly grasp the key points.

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 description covers the essential operational flow (payment steps, limits, and the grace-clearing effect) and explains the key parameters, but it omits error handling, what the response contains, and any failure contingencies. Given there is no output schema and no annotations, this represents a notable gap. An agent might need to probe for error behavior, but the core invocation path is clear enough to start.

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 only 33% (only address has a description). The description compensates by explaining the payment flow for payment_b64 ('call without payment_b64 for requirements, retry with it') and interpreting amount_microusd through the min/cap and rate context. It clarifies that amount is in micro USD and tied to the published rate, adding meaning beyond the raw integer type. This is a strong mitigation of the schema's sparse documentation.

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 precisely states the action ('Top up storage credit') and adds critical specifics: it funds checkpoint storage at a published GB-month rate, with a minimum of $1 and a cap of $100. It also clarifies the payment mechanism (x402) and the immediate effect of clearing read-only grace, leaving no ambiguity about what the tool accomplishes. This is a specific verb+resource combination that stands apart from siblings like locker_send or locker_status.

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 implies when to use this tool (to add prepaid credit and clear grace) but does not explicitly contrast it with alternatives or state exclusion criteria. It references locker_send for the payment flow, which suggests they share a payment pattern, but it never says 'use this instead of X when Y' or mentions when not to use it. The guidance is adequate but relies on the reader to infer the selection context.

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