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

Annotations cover readOnly/destructive/openWorld, but the description adds critical info annotations cannot express: the paid-per-call model ($0.0045 USDC), the x402 payment rails, the automatic-payment behaviour of x402 clients, and a free sample call. These are exactly the operational facts an agent needs before deciding to spend. It stops short of latency or error/refund behaviour, keeping it out of the 5 range.

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?

Front-loaded with resource and fields, then usage modes, then params, then pricing and sample. Every sentence carries information an agent needs. Slightly dense but no filler; a 5 is reserved for tighter structures.

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 data tool with no output schema, it covers inputs, filtering modes, cost, payment mechanics and a free-try path. The only gap is an explicit statement of return shape (e.g. a list of per-coin objects), which is partially addressed by the field enumeration. Adequate and well-rounded.

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 50% (coins documented, limit not). The description compensates by restating both params with constraints: coins optional max 50 with a usage example, limit 1–50 default 10 and the crucial rule that it applies only when coins is omitted. That last sentence adds meaning the schema does not express, lifting it above the baseline 3.

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 first sentence names the specific resource (Hyperliquid perpetual futures market data) and enumerates exactly what fields are returned: mark/oracle price, 24h change, funding rate and APR, open interest, 24h volume, max leverage. This is a precise verb-and-resource statement that an agent can match to intent without opening a 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 states the two modes clearly: pass coins for specific markets, omit them to get top markets by open interest, plus a worked example. It does not explicitly say when to prefer this over the sibling `perp_funding`, though the field list makes the distinction inferable. Strong but missing an explicit alternative-tool pointer.

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