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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered; the description goes further by disclosing that rows are sampled rather than complete, that labels are mechanical rule-derived values under a linked disclosure, and that the payload carries provenance (endpoint and fetch time). That is meaningful context an agent cannot get from the schema. It stops short of describing rate limits, sorting/tiebreak behavior, or what an empty result means.

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?

Purpose is front-loaded in the first sentence, followed by the differentiating caveat, then the label semantics. The long clause stack about labels and the prohibitive disclaimer is dense, but each part earns its place by preventing a specific misuse (restating labels as skill judgements).

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 output schema, the description carries the burden of explaining return shape, and it does describe rows, the labels object and its three components, and a provenance field. The link to the label rules covers the recursive detail economically. What is thin is the actual row field list (rank, address, raw numbers) which is only revealed in the response_format parameter text.

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 every parameter has an inline description with defaults and enums, so the baseline is 3. The prose contributes only tangentially — 'the four published windows' and the metric list loosely echo the enum values — and adds no syntax, interaction, or format guidance beyond the schema.

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 resource (Hyperliquid wallets), the ranking dimensions (PnL, ROI, volume, account value) and the scoping (sampled, across time windows). It also pre-empts a likely confusion by stating it is not the official leaderboard. It never names a sibling, so an agent must infer the split with tape_wallet_analysis or tape_markets_radar on its own.

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 noun 'leaderboard' plus the sampling caveat, but there is no explicit when-to-use, when-not-to-use, or named alternative among the ten siblings. The 'sampled' framing hints this is not a complete universe, yet the description never tells the agent which tool to reach for when it needs exhaustive or single-wallet coverage.

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