execute_swap

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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely useful context beyond that: the tool returns unsigned calldata and FarmDash explicitly does not broadcast it, meaning the caller owns the on-chain submission step. It omits what the signature/nonce are consumed against and any 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?

The core sentence is front-loaded and efficient, but the bracketed capability/tier/API/authority prefix is dense internal routing metadata that competes with the actual behavioral statement. Three sentences carry roughly two sentences of real information.

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 13-parameter destructive-looking operation with no output schema, the description does cover the important boundary (returns calldata, does not broadcast) and the gating tier. However, with 15% schema coverage it leaves most required inputs unexplained and says nothing about what the calldata response contains or what to do with it.

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 description coverage is only 15% across 13 parameters and 10 required fields, and the description adds almost nothing: signature and simulationId are only obliquely referenced via 'signed' and 'after a fresh successful simulation'. Nonce, intentId, protocol enum, slippage, and the from/to chain-token pairing are undocumented in both places.

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: validate a signed token-swap request after a successful simulation and return transaction calldata. The 'Compatibility route' framing plus 'does not broadcast' and 'execute_approved_intent remains unavailable' distinguishes it from the generic execution sibling, though it does not name which of the many swap siblings (confirm_swap, prepare_autonomous_swap, simulate_swap_execution) to prefer.

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?

Provides a real precondition: a fresh successful simulation must exist and the request must carry a signature. It also notes the generic execute_approved_intent path is unavailable, which implies this is the fallback. But it never says when an agent should choose this over confirm_swap or prepare_autonomous_swap, leaving the routing to inference.

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