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

Annotations already declare readOnly, non-destructive and open-world, and the description reinforces that nothing is changed. Beyond annotations it adds the information an agent most needs to know: per-call cost, a 25-call free tier, failed calls free, and the 20-level cap, which also explains why idempotentHint=false despite being a read (repeat calls incur charges). It stops short of stating data freshness or latency.

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 returned fields are front-loaded in the first sentence, with usage and cost following, so the ordering works. The pricing/billing tail is denser than strictly needed for tool selection and slightly blurs the focus, though it is genuinely actionable 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?

There is no output schema, so the description carries the return-shape burden itself — and it does so by enumerating bids, asks, mid, spread in USD and bps, and summed depth per side. Combined with the level cap, source (public API) and cost model, an agent has everything needed to call this 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?

Schema coverage is 100%, so both parameters (coin, levels) are already fully documented with defaults and the 1-20 range, establishing the baseline of 3. The description only restates the defaults and adds a redundant 'Example: coin=BTC' rather than adding new meaning.

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 — the live order book of a Hyperliquid perpetual — and enumerates the delivered fields (best bid/ask with price, size, order count, mid, spread in USD and bps, per-side depth). That is enough to separate it from siblings such as hyperliquid_prices, hyperliquid_candles, hyperliquid_market and polymarket_orderbook without opening any schema.

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 concrete use cases: judging liquidity and slippage before a trade, market-making and arbitrage checks. It does not name an explicit alternative or a when-not condition (e.g. use hyperliquid_prices for a spot quote), so routing is clear but not fully disambiguated.

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