Redeem shares → USDC (zap-out lifecycle)

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

Annotations already declare destructive=true, idempotent=false and openWorld, but the description adds genuinely new behavior: the call is asynchronous, returns status:"pending" that is not settled, requires app-wallet boundary signatures server-side, and is real-money gated. It does not explain slippage failure behavior or what happens on expiry/partial fill, which keeps it below a 5.

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 gating warning and the operation, then lifecycle and follow-up in the right order; every sentence carries a distinct instruction. Slightly dense and jargon-heavy (zap-v2, escrow basket), but nothing is padding.

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, asynchronous, no-output-schema tool this covers the essential loop: invoke, expect pending, poll via zap_status, verify via app_wallet. It omits failure/rollback behavior and slippage bounds interpretation, which are the remaining gaps for an agent to call it safely.

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?

With only 40% schema description coverage, the description compensates for the most error-prone parameter by clarifying that `shares` is RAW 6-decimal units — meaning beyond the schema pattern. However `slippageBps` is unexplained in both schema and description, and `vault` semantics are left entirely to the pattern, so compensation is partial.

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+resource with mechanism: 'Open a zap-v2 redeem (burn shares → escrow basket, oracle-free pro-rata)'. It clearly separates itself from zap_v2_cancel/zap_v2_update_envelope and from deposit by naming the direction of the lifecycle.

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?

Explicitly tells the agent what to do after calling (poll zap_status, verify with app_wallet) and what NOT to do (do not repeat redeem to poll). It also flags the conditional confirmPhrase gate and its operator dependency, so the agent knows when human confirmation applies.

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