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

Annotations already mark this read-only/idempotent/non-destructive, and the description adds substantial behavioral context beyond them: the full state lifecycle, the refunding and terminal failure outcomes (refunded, failed, expired), the long-poll loop semantics, and a safety rule for the payment field ('sign only if paymentCheck.safeToSend'). This is real operational context the agent needs to poll and to avoid signing an unsafe payment.

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?

Dense but efficient — every clause carries polling or safety information, and the state progression is front-loaded. The opening 'Step 3.' fragment is slightly cryptic without external ordering context, and the telegraphic style trades readability for brevity, but no sentence is wasted.

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-value explanation is unnecessary, and the description covers the state lifecycle, terminal outcomes, long-poll loop, and the payment-safety gate — enough for a 6-parameter polling tool. It omits what 'detail: lean/full' changes and how verify is used, minor gaps given the existing schema descriptions.

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 already 83%, but the description adds meaning beyond the schema: waitSec guidance (25), that sinceState should equal the last observed state, and that payment is 'what your wallet will sign' gated on paymentCheck.safeToSend. These are semantic rules not present in the field descriptions, though detail/verify/get parameters are not elaborated.

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 names the resource (swap) and its purpose through a concrete state machine (waiting_for_funding -> deposit_detected -> swap_processing -> completed, or refunding/terminal_failure) plus the long-poll mechanic, so an agent understands this is a status-polling tool. It doesn't explicitly distinguish itself from list_swaps, which also surfaces swap state, so it stops short of a 5.

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 explicit when-to-use triggers ('Call it before funding or showing a deposit again') and prescriptive polling instructions ('Long-poll with waitSec 25 and sinceState = the last state; repeat next until terminal'). The terminal condition and the repeat loop are both stated, leaving nothing to inference.

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