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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, but the description adds real behavioral context: the preview-until-confirm gate, that an unfinished provider payment is returned for human approval, and that idempotency_key replays the same result rather than re-charging. These are the kind of side-effect and async-flow details an agent needs before spending money. It still doesn't mention currency, limits, or failure modes.

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?

Front-loaded with the core action, then layered constraints in short sentences. The second sentence restates what the first already implies about saved cards, so there is minor redundancy, but nothing is bloated.

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 destructive, open-world, money-moving tool with no output schema, the description covers charge gating, async approval, idempotency, and payment-method defaults. Missing pieces are unit/currency of amount and what the preview response contains, which matter for an irreversible charge.

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 50%, so the description must carry weight, and it does: it explains the default-saved-card fallback when payment_method_id is omitted and clarifies the replayed-result semantics of idempotency_key beyond the schema's own wording. The amount parameter's semantics (currency, units) are never stated.

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?

"Charges a saved card and adds the amount to this swift_platform wallet" gives a concrete verb, mechanism, and target resource, which distinguishes it from generic wallet tools. It explicitly names the sibling topup_with_saved_method, though the phrasing ("uses the same ... as") explains a shared implementation rather than cleanly stating how the two tools differ in outcome.

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?

Clear operational conditions: omitting payment_method_id charges the default card, and nothing is charged until confirm is true. It also rules out raw card input ("Card numbers are not accepted"), implicitly routing agents to saved methods. It stops short of explicitly saying when to pick this tool over topup_with_saved_method or list_payment_methods first.

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