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

With no annotations, the description carries the full behavioral burden. It does disclose real behavior beyond the schema — fixed FX at KES 133 = $1, wallet credited in USD, 'Free; the charge happens at payment' — which is genuinely useful. However, for a payment-initiating mutation it omits whether repeated calls create duplicate top-ups (idempotency), what 'confirm' does, whether a phone prompt is triggered, and what is returned (a URL, a pending state).

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?

Two dense sentences, front-loaded with the action and payment channels, followed by the pricing/FX constraint. No filler, though the pricing sentence could be tightened and would read better after a line about the amount parameter.

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?

Six parameters, 50% schema coverage, no annotations and no output schema, yet the description covers only channels and FX. For a financial action that spends real money, it should say what is returned, whether the call is repeatable, and what amount_usd/confirm control.

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 50%, and the description adds nothing about the four undocumented parameters: 'phone', 'confirm', and especially 'amount_usd' are never mentioned, so an agent cannot tell what amount_usd represents, whether it is required (the schema lists no required fields), or how currency interacts with it. The FX sentence adds meaning only for 'currency', which the schema already annotates as 'the charge is always KES'.

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 states a specific verb and resource ('Create a top-up for the wallet') and names the two accepted payment channels (card, mobile money with M-Pesa/Airtel examples). It is clearly distinguishable from fikra_check_topup_status and other billing siblings, though it never names an alternative explicitly.

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?

Usage is implied by the verb and the payment-channel enumeration, but the description gives no explicit when-to-use, no prerequisites (auth, phone ownership), and no pointer to fikra_check_topup_status for follow-up. An agent must infer the workflow entirely from the tool name.

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