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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses the stale-data failure mode (503, never billed), the exact per-call cost (0.005 USDC), and the x402 payment rails (USDC on Solana, Base, Polygon, Arbitrum, Arc). Billing and failure semantics are exactly the behavioral context an agent needs before calling a paid endpoint.

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?

Three sentences, front-loaded with the use case, then what is returned, then failure/billing terms. Every clause carries distinct information and nothing is repeated from the schema or annotations.

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 shape needs no elaboration, yet the description still summarizes the payload (total USD, long/short split, prints, top 5 symbols). Combined with cost, payment options, and stale handling, an agent has everything needed to decide and invoke correctly.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to clarify and it correctly does not invent any input surface. The stated scope (60-minute window, all USDT perps) effectively documents the implicit query dimensions.

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 a specific verb and resource ('what is being liquidated right now') and pins the scope tightly: last 60 minutes, every USDT perp, with total USD, long/short split, prints and top 5 symbols. That is enough to distinguish it from broader history tools, though it never names a sibling explicitly despite the crowded liq_* family (get_liq_feed, get_last_liquidation, get_recent_liquidations).

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?

'Use when an agent needs to know what is being liquidated right now' gives a clear trigger, but there is no when-not and no comparison against the many near-identical siblings (get_liq_feed, get_recent_liquidations, get_last_liquidation, get_liq_history). The 'right now' framing implies recency-scoped usage but leaves the agent to infer which liquidation tool to pick.

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