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

Annotations already cover read-only and open-world, so the description correctly adds traits the annotations cannot convey: the response is signed, it is explicitly not investment advice, and each call costs $0.01 USDC via x402 on Base or Solana. That payment prerequisite materially affects whether an agent can invoke it. It still doesn't mention latency, rate limits, or whether the x402 handshake is required per call or per session.

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?

One front-loaded sentence naming the domain, followed by the signal inventory and then the commercial/legal caveats. The comma-separated metric list is dense but every item is a distinct returned field, so nothing is filler. Slight cost in scanability for readers looking for the action verb.

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?

No parameters and no output schema, so the description carries the return-value burden — and it does list the signals, plus signing, disclaimer, and payment. For a zero-input read tool that is largely sufficient. Missing only freshness/cadence of the data (how recent is the 24h change, when is it snapshotted) and any indication of response size.

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?

There are zero input parameters, so there is nothing for the description to document; the baseline for a no-param tool applies. The metric list effectively doubles as a description of what the (absent) output schema would contain, which is a small bonus rather than a 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?

States a specific resource (market-wide crowding on Hyperliquid) and enumerates the exact signals returned — breadth of 7-day moves, 50%+/100%+ gainers, funding extremes, open interest, BTC/ETH funding percentiles, Wikipedia attention. That is far more specific than a bare name restatement. It stops short of explicitly contrasting itself with near-siblings like crowd_perp, crowd_states, or perp_full, which an agent would need to disambiguate a market-wide view from a perp-level one.

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?

No when-to-use framing, no conditions, and no named alternatives among the many crowd_*/perp_* siblings. The only usage-adjacent content is the commercial one (price, payment rails), not task guidance.

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