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

Goes well beyond the annotations: it discloses that calls are paid (x402 USDC/Scout credits), that refusals refund the debit, that refusal codes follow a published taxonomy, that unpaid calls return a payment_required challenge, and that the tool polls /v1/resolutions/:id until horizon_end. The only mild tension is that readOnlyHint=true while the description says the call debits/refunds credits, but since the payment mechanics are fully spelled out the agent is not misled.

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 description is oversized and back-loaded: the first sentence is payment plumbing rather than the tool's purpose, and 'after paying, poll /v1/resolutions/:id until horizon_end' is stated twice. The refusal codes are likewise given twice ('out_of_scope / insufficient_sample' then the full taxonomy), so meaningful redundancy undercuts the density 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?

With an output schema present and annotations covering safety/open-world hints, the description supplies the remaining critical context: payment requirement, refund policy, refusal semantics, current unavailability, and polling behavior. It is essentially complete for invocation decisions, missing only a crisp statement of the quantity being estimated and the horizon semantics.

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 only 50% (asset is documented, payer is not), but the description compensates for payer by giving three concrete settlement paths (tool argument `payer` as a Base 0x… address, `x-tollbridge-payer` header, or an x402 PAYMENT-SIGNATURE). It also clarifies the asset domain ('any symbol the venue universe lists — not only BTC/ETH/SOL'), adding meaning beyond the schema pattern.

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 never plainly states the analytical purpose (e.g. 'assesses market-wide liquidation risk for an asset over a horizon'); it opens with the payment rail and availability status. The scope is inferable from 'the market-wide liquidation tape' and the implicit probability output ('never fabricate a probability'), and it is loosely differentiated from siblings like tollbridge_token_risk/transaction_risk, but the core verb+resource is left to the name/title.

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 states the tool is NOT available yet and the exact preconditions that turn it on (operator mounts a Hyperliquid node trade stream at NODE_TRADES_DIR, sets LIQUIDATION_SOURCE=node_trades, and 24 hourly observations). It also names the alternative data sources (per-wallet fills, node trade files) and points at tollbridge_universe for valid assets. It stops short of naming a sibling tool to call instead, which keeps it off a 5.

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