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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: 'deposit — credit a deposit that already landed on chain', 'withdraw — withdraw to the principal's operator wallet (the only destination)', 'register ... returns its one-time key', and the note that omitting the signature yields the exact message to sign. Only the irreversibility/error behavior of order and withdraw is left unstated.

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 and the sibling escape hatch are front-loaded, then the action glossary follows in one dense block. Given 20 parameters and 7 dispatchable actions, the size is justified, though the run-on action enumeration ('account, deposit route, orders, withdrawals, settlement records') is slightly muddled before the per-action breakdown.

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 multi-action dispatcher with 20 optional params and no output schema, the description does cover all seven actions plus some return behavior (one-time key from register, reconcile reading from settlement) and key constraints. It omits which parameters each action actually requires and how the api_key is obtained, which an agent would still need to discover from the schema alone.

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 100% and every parameter already carries its own '(actions: X)' tag, so the schema does the heavy lifting. The description's action list largely restates that mapping rather than adding parameter-level meaning (units format, TIF semantics, market values are all in the schema). Baseline 3 is correct here.

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 description names the concrete scope (Taifoon orderbook, spot ETH-USDG on Robinhood Chain) and enumerates all seven actions with a one-clause meaning each, so an agent knows what surface this tool covers. It distinguishes itself from taifoon_vault explicitly but not from the many siblings with overlapping names/actions (taifoon_buy, taifoon_sell, taifoon_register, taifoon_account), so it falls short of full sibling differentiation.

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?

It gives one explicit routing rule — 'For tenant vaults use taifoon_vault' — which is genuine when-not guidance. However, with 15 siblings and several sharing action names (buy/sell/register/account), the description never says when this venue tool is the right choice versus those alternatives. Usage for the remaining actions is only implicit in the action list.

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