Loosen pinned floors on a stalled zap-v2 escrow

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

Annotations declare destructiveHint=true and non-idempotent, and the description adds context beyond them: real-money gating, that the tool reads live pinned minOuts rather than accepting absolute values, the monotonic onchain clamping rule for newSlippageBps, and the human-confirmation gate. This is high-value behavioral disclosure.

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 risk warning and the core verb, and nearly every sentence adds operational information. Density is high and reads slightly like jargon-dense shorthand, but there is little waste.

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, non-idempotent mutation with no output schema, the description covers return content ('the exact loosening applied (old→new)'), the gating model, and the failure fallback. It does not describe side effects on the escrow beyond floors or any post-condition guarantees, which is a modest remaining gap.

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 20%, so the description must compensate, and it largely does: it explains loosenPct semantics (relative relaxation, default 5), extendSecs (optional expiry extension), and the newSlippageBps clamp floor/ceiling. The upper/lower bounds it repeats for loosenPct and newSlippageBps already exist in the schema, and vault is left unexplained, so it falls short of full compensation.

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 (LOOSEN) and resource (per-leg min-out floors on a zap-v2 escrow), plus the triggering condition (stuck mid-crank escrow). An agent can distinguish it from zap_v2_cancel and the swap/deposit siblings without opening a 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 explicit when-to-use ('so a stuck mid-crank escrow can finish'), a precondition ('REAL-MONEY (gated)'), and names the fallback route ('If it still will not fill, cancel'), which maps to the zap_v2_cancel sibling. Nothing is left to inference.

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