set_settlement_address

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

No annotations exist, so the description carries the full disclosure burden. It does add real context: per-leg semantics, the maker/taker leg-role mapping, and the ordering constraint before funding. It omits what happens on a second call (overwrite/idempotency), whether the caller must be a party to the swap, and any address validation or error behavior — gaps that matter for a mutation tool with zero annotation coverage.

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?

Purpose is front-loaded in the first clause, followed by the funding prerequisite and then the leg-disambiguation rule — a sensible priority order. The maker/taker sentence is dense but each sentence carries distinct information; only minor overlap with the schema's own `leg` description.

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 four-parameter mutation tool with no annotations and no output schema, the description covers when and how to call it but not the outcome: nothing about the response, whether the address can be re-set, or what errors arise from an invalid or wrong-chain address. Adequate to invoke, thin on what to expect.

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%: `leg` and `chain` are already described in the schema, but the description goes further on `leg` by explaining the maker funds leg a and receives on leg b while the taker is the reverse, and it clarifies that `address` is the caller's own receive/refund address rather than an arbitrary counterparty address. `swap_id` receives no added meaning, but it is a self-evident UUID identifier.

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?

States a specific verb and resource — set the caller's receive/refund address for an agreed swap, per leg — and scopes it to a prerequisite of HTLC funding, which cleanly separates it from fund_leg, claim_leg and refund_leg in the sibling list. An agent can tell what this does without opening the schema.

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 a clear trigger ('Required before the HTLC can be funded') and an explicit conditional rule for when to supply `leg` (only when both legs are on the same chain). It does not name an alternative tool or state exclusions, but the sequencing relative to fund_leg is unambiguous.

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