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

Beyond readOnlyHint/openWorldHint the description adds real operational context: sub-second-ish latency, scope exclusions (no PnL history, cannot guarantee stop coverage), that it changes nothing, and that it is a paid per-call endpoint at 0.28 USDC on Base via x402 at a specific URL. It stops short of 5 because "with sources, timestamp and limits" is vague about what limits means and the payment/identity block mixes promotional content into 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?

The purpose and scope are front-loaded, but the body then spends several sentences on token-fee economics (GHOST77 0xC434...), ERC-8004 agent #348263, Virtuals ACP IDs and payout wallet addresses. That identity/monetization material does not help an agent decide to call the tool and dilutes the actionable parts.

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 no output schema, the description does the work of listing returned fields (positions, margin utilization, liquidation distance, trigger orders) plus sources and timestamp, and it discloses cost, latency and read-only behavior. An agent has enough to call it correctly; only the exact semantics of trigger-order coverage and "limits" remain fuzzy.

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%, so walletAddress and the optional tokens filter are already fully documented with patterns and a default-omitted behavior. The description only echoes the input names and adds a trivial example object, no new semantics. Baseline 3 applies.

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?

Opens with a specific framing ("How close a Hyperliquid account is to trouble") and enumerates the concrete outputs: open positions, margin utilization, liquidation distance, observed trigger orders. It is clearly a position-risk snapshot rather than a market scan or a trade idea, which separates it from most siblings. It doesn't name a nearest alternative (e.g. hl_liquidation_map or wallet_watch_alert), so it stops short of 5.

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?

"Read-only snapshot: no PnL history, cannot guarantee stop coverage" functions as a when-not signal, and "Seconds" implies a lightweight call. But there is no explicit statement of when to prefer this over hl_liquidation_map, base_protocol_health, or wallet_watch_alert. Usage is implied rather than directed.

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