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

Annotations already declare readOnlyHint and openWorldHint, and the description adds genuinely load-bearing context beyond them: response latency ("Seconds"), data provenance (public HL API, sources and timestamp), a not-financial-advice disclaimer, and — most importantly — that the call is paid 1.1 USDC on Base via x402. The long tail of token fee, payout wallet, and ERC-8004/Virtuals identity metadata is verifiable boilerplate rather than invocation-relevant behavior, keeping it from a 5.

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?

The first sentence is dense, front-loaded, and does the real work. The remainder is a single run-on block where payment terms, identity proof, and token fee are interleaved; the identity/wallet attribution is promotional filler that does not help an agent decide or invoke.

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 paid, read-only, single-parameter tool with no output schema, the description covers the input format, the metrics returned, freshness, sourcing, and cost — enough to call it correctly. Only the fee/identity boilerplate is surplus relative to that completeness.

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% and the schema already documents the symbol format and BTC default, so the baseline is 3. The description's "Input: market, e.g. {\"market\":\"ETH\"} (default BTC)" restates the schema with a concrete call example but adds no new semantics such as accepted casing or unsupported symbols.

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 opening clause names a specific resource and verb-like framing ("What holding a Hyperliquid perp costs now") and enumerates the exact outputs: hourly/annualized funding, who pays, 24h/7d averages, predicted funding, OI, volume, mark vs oracle premium. This clearly separates it from siblings like funding_arb_scan (cross-venue arb discovery) or hl_quick_trade_idea (trade suggestions).

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 by the framing ("what holding costs now") rather than stated, and no sibling is named as an alternative or excluded. An agent can infer this is a point-in-time funding lookup, but nothing tells it when to prefer this over funding_arb_scan or hl_quick_trade_idea.

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