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

With no annotations, the description carries the full behavioral burden, and it does disclose some real traits: the data is measured historically rather than forward-projected, there is a free 3-row preview versus a paid side, and the x402 paths imply a payment-gated endpoint. It does not state cost, rate limits, auth requirements, or how the paid side is unlocked, and the sentence trails off mid-word ('Measured: the forwa'). That is partial disclosure for a read tool with zero annotation coverage.

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 text is a dense run-on that mixes endpoint URLs, marketing framing ('REALIZED not advertised'), and an eight-field dump into one block. It is truncated mid-sentence, which leaves the reader with a dangling clause instead of a complete thought. The core claim is front-loaded, but substantial wording does not earn its place.

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?

With no parameters and no output schema, the description does the right thing by enumerating the returned row fields, which partially compensates for the missing output schema. But several fields are unexplained (fits_45u, divergence_x, consistency), the preview-versus-paid mechanics are vague, and the truncated final sentence leaves the measurement methodology unstated. Adequate but with clear gaps for a tool whose whole value proposition is data semantics.

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?

The tool takes no parameters, so there is no parameter meaning to add and the baseline of 4 applies. The field names listed (collector_24h_pct, forward_24h_pct, divergence_x, net_of_cost_24h_pct, consistency, premium, book spread, fits_45u) describe the return payload rather than inputs, which is useful but belongs under output disclosure.

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 conveys that this ranks realized perp funding returns over 24h, net of round-trip cost, across HL perps and the HIP-3 dexes, and explicitly contrasts itself with feeds that rank forward ctx.funding. However, it opens with a noun phrase ('Perp funding edge') rather than a verb+resource, and the first third of the text is spent on raw endpoint paths rather than stating what the tool returns to the caller. The purpose is recoverable but requires parsing.

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?

There is an implicit contrast ('Every other feed ranks the forward ctx.funding; this ranks what fundingHistory actually applied'), which hints at a selection criterion, but no explicit when-to-use or when-not-to-use statement. The definition never says how this differs from sibling akari_hyperliquid_funding or akari_hl_roundtrips, nor when a caller should prefer it. The 'Free 3-row sample' line hints at a paid tier but gives no guidance on that decision.

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