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

Adds substantial behavior beyond the annotations: paid x402/Scout credit flow with three payment mechanisms, the structured payment_required challenge on unpaid calls, the guarantee of 'never fabricated data', refund-on-refusal, and the resolver tape ('emit and resolver share that tape'). This is well beyond the readOnlyHint/openWorldHint/idempotentHint annotations, though the polling endpoint and horizon_end mechanics remain terse.

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?

'After paying, poll /v1/resolutions/:id until horizon_end' is stated verbatim twice, and the three payment rails are spelled out at length. The decision rules are front-loaded reasonably, but the redundant payment/polling prose bloats a description that leaves core input semantics unexplained.

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?

An output schema exists, so return values need no explanation, and the payment/decision logic is well covered. However, for a 4-parameter tool with a required nested `candidate` object and a name/description identity mismatch (transaction vs account risk), the definition is not complete enough for an agent to assemble a correct call without guessing.

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 25% — only `asset` carries a schema description. The description clarifies `payer` (a Base 0x address, alternative to the header) but says nothing about `address` or, critically, the required nested `candidate` object (tx_hash, log_index, direction, amount, usd_value, counterparty), leaving the main input shape undocumented in both schema and prose. It does not compensate for the coverage gap.

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 states a fairly specific computation — Hyperliquid account liquidation proximity, mapped to {allow, review, block} with explicit 5%/15%/5× leverage thresholds — which is more than a tautology. But the identity is muddled: the tool name says 'transaction_risk', the title says 'account risk', and the description talks only about an ACCOUNT's liquidation proximity while the schema requires a `candidate` transaction. No distinction is drawn from sibling tools like tollbridge_liquidation_risk or tollbridge_token_risk.

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?

There is extensive guidance on HOW to pay and poll, but nothing on when to choose this tool rather than tollbridge_liquidation_risk, tollbridge_token_risk, or tollbridge_wallet_intelligence. No trigger conditions or exclusions for the analysis itself are given; the agent must infer usage from the tool name.

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