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

Beyond annotations (readOnly/idempotent/non-destructive), it discloses non-obvious behavior: it is premium-gated with two auth paths, and critically it 'seeds a baseline on first call', meaning the first invocation will not return alerts. That is exactly the kind of trait an agent would otherwise misinterpret as an empty result.

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?

Dense but efficient: the premium/key requirement is front-loaded, then the core definition and the distinctive 'full exits' / 'baseline seeding' details. The trailing 'analytics only, not investment advice' is boilerplate but short.

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 an output schema present, return-shape explanation is unnecessary, and the description covers the auth path, the baseline-seeding gotcha, and the core semantics. Minor gaps remain around topN and the dex scoping caveat that the schema documents but the description doesn't reinforce.

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 80%, so most parameters are already documented in the schema. The description adds conceptual meaning to the cohort/threshold combination ('net long/short notional shift beyond a USD threshold') but says nothing about topN or the dex='all' wallet-limit caveat, so it only marginally exceeds 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 description names a concrete resource and behavior: recent net long/short notional shifts in whale cohorts beyond a USD threshold within a lookback window, with full-exit detection. This clearly separates it from a static holdings tool like hl_whale_positions (flow/change vs. position snapshot), though it does not name that sibling explicitly.

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?

It gives a concrete prerequisite and routing instruction — call hl_request_free_key first or pay per call via x402 — and frames the use case as 'who opened/closed what in the last hour'. It stops short of explicit when-not conditions or naming the alternative tool for position snapshots.

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