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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral facts beyond that: the destination is immutable once saved, and saving does not trigger a transfer. It still omits whether the write can be rolled back or what happens on a second call with a different address.

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 sentences, no filler, and the gating condition is front-loaded before the effect. Every clause carries information an agent needs before calling.

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 3-parameter write tool with no output schema and low schema coverage, the description covers the trigger and immutability but leaves the parameters and the post-call outcome unexplained. It is minimally adequate rather than complete.

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% (just sessionId documented as 'returned by create_swap'), and the description adds nothing about any parameter. orderId and refundAddress are undocumented in both places, and for a refund address the agent has no hint about expected format, chain compatibility, or length constraints beyond the schema's maxLength.

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 verb+resource are clear from the title and the second sentence ('Saves one immutable destination'), and the note that it 'does not start a transfer by itself' distinguishes it from create_swap. It stops short of plainly naming the resource (refund address) in the body text, relying on the title for that.

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 opening sentence gives an explicit, machine-checkable precondition: use only when get_swap returns customerState { kind: 'action_required', action: 'refund_address' }. It also implicitly excludes the transfer flow by stating it does not start a transfer, so the agent knows exactly when to reach for it versus create_swap.

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