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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered by structured fields. The description adds genuinely useful non-annotation behavior: public data only, ~3 min refresh, stale (>15 min) never charged, and the $0.002 USDC x402 payment flow from the caller's own wallet. This is richer than the annotations alone and helps the agent understand cost and freshness risk.

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 the core capability before the freshness, pricing, and disclaimer clauses, and every sentence carries distinct information (scope, data policy, payment, disclaimer). The 'Not financial advice' boilerplate is the only filler, but it is defensible for a financial-signal tool.

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 must carry the return semantics, and it does name the shape (ranked top positive/top negative hourly funding, annualized, per side). Combined with the freshness and payment rules, an agent has enough to call it correctly, though the exact response structure and the 402 challenge/retry flow could be spelled out more.

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 100%, so coin, limit, and payment_signature are already documented in the schema. The description adds only marginal semantics: that omitting coin yields the all-perps ranking and that results are 'per side' (implying limit applies per side). Baseline 3 is appropriate when the schema carries the parameter detail.

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 verb and resource (rank funding-rate extremes across all Hyperliquid perps) plus the exact metric (top positive/negative hourly funding, annualized) and the optional single-coin scope. An agent can distinguish this from siblings like hyperliquid_whale_positioning or hyperliquid_market_brief 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?

The 'all perps ... or one coin' phrasing implies when the coin parameter applies, and the staleness/charging rules tell the agent the data must be fresh. However, it never explicitly contrasts itself with the sibling tools (market_brief, whale_positioning, feed_status) or states when to prefer one over the other, so usage is implied rather than guided.

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