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

Annotations already cover read-only, idempotent, and non-destructive, so the description correctly spends its words elsewhere: it discloses the premium/API-key gating and pay-per-call option, and flags that results are an estimate over the cohort rather than exchange-wide truth. Minor gaps remain (cost magnitude, freshness/caching of the snapshot), but the value-add beyond annotations is real.

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?

Two tight sentences: a bracketed premium/auth tag, then one dense sentence carrying purpose, output shape, scope caveat, and disclaimer. Front-loaded with the gating constraint an agent must handle before calling, with no redundant restatement of the title.

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?

Output schema exists, so return structure needn't be explained, and the description covers the auth path, the analytic (non-advice) nature, and the estimation scope. The remaining hole is topN — an agent cannot tell what it limits (cohort size? cluster count?) from either field.

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 60%, and the description does illuminate bucketPct/maxDistancePct conceptually via 'bucketed by % distance from mark' and the cohort framing. However, topN has no description in either the schema or the description, and cohort membership syntax is unaddressed, so the undocumented portion is not compensated for.

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?

Names a specific verb+resource: estimated liquidation clusters for a coin, drawn from a whale cohort's open positions, with the output shape (bucketed liq prices, notional-at-risk, nearest cascade levels) stated inline. The explicit scope caveat 'estimate over the cohort only (not exchange-wide)' separates it cleanly from exchange-wide siblings like hl_whale_positions or hl_portfolio_risk.

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?

Gives a concrete prerequisite path — call hl_request_free_key first or pay per call via x402 — so an agent knows how to unlock access before invoking. It also states a scope boundary (cohort-only, not exchange-wide). It never explicitly says when to prefer this over hl_whale_positions or hl_coordination_scan, so it stops short of full when/when-not guidance.

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