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

Annotations already cover read-only/idempotent/non-destructive, and the description still adds real value: premium auth path (API key, hl_request_free_key, x402 pay-per-call), cohort fallback chain, and a candid disclosure that weights are judgement-based and unvalidated, pointing at the `calibration` field. That is exactly the behavioral context annotations cannot carry.

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-loads the premium/auth gate in brackets, then the core behavior, then the caveat — a sensible order. It is dense with parentheticals and a long label list, but nearly every clause earns its place against a tool this complex.

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 values are covered, and the description supplies the auth model, cohort sourcing, and the calibration caveat. The remaining gap is the unexplained pagination/ranking parameters (topN/limit/offset), which is minor but real.

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 only 20% (just `cohort`), so the description must compensate — it explains cohort resolution but says nothing about topN, limit, offset, or lookbackDays. In particular the topN vs limit distinction (defaults 50 vs 25, both max 100) is left ambiguous, which is user-impacting.

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 a cohort of wallets by a composite screening score') plus the secondary output (behavioral labels: whale, sharp, scalper, etc.). It is clearly separable from siblings like hl_trader_report (single wallet) and hl_vault_screener (vaults) without opening either 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?

Gives an explicit use case ('shortlist wallets to inspect') and an explicit anti-use ('not as a forecast'), and routes detail-seekers to hl_score_calibration and unauthenticated users to hl_request_free_key. It does not, however, say when to prefer a different screener sibling over this one.

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