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

With no annotations, the description carries the full burden. It usefully discloses the derived fields returned (relevant since there is no output schema) and the depth-level scoping, but says nothing about read-only nature, payment/auth requirements common to this x402 family, rate limits, or error behavior on an unknown perpetual.

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?

Two sentences, front-loaded with the resource and enumerated return values, each sentence earning its place. Minor promotional phrasing ('a trading agent actually uses', 'before you send it') is light enough not to bloat it.

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?

For a read-only book tool with no output schema or annotations, describing the returned microstructure fields is valuable and largely sufficient on the output side. However, the unresolved coin-vs-symbol ambiguity and absent payment/auth context leave notable gaps for three fully undocumented parameters.

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 0% and the description must compensate, but it only obliquely covers the inputs — 'one perpetual' gestures at the asset and 'the requested levels' at depth. It never resolves the ambiguity between the two overlapping params, coin and symbol, nor specifies depth syntax, so the agent is left guessing.

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 concrete resource (Hyperliquid L2 order book for one perpetual) and enumerates exactly what derived values come back — best bid/ask, spread in ticks/bps, midpoint, depth imbalance. That content makes it clearly distinguishable from siblings like x402-hyperliquid-mids or x402-hyperliquid-candles, though it never names an alternative explicitly.

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?

Usage is implied rather than stated: 'Thin books and lopsided depth are how you spot a bad fill before you send it' signals a pre-trade check, which is real guidance. But there is no explicit when-to-use vs. a sibling (e.g. mids or depth) and no when-not-to-use or prerequisite.

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