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

Annotations already cover read-only, idempotent, open-world and non-destructive behavior, so the bar is lower, yet the description adds substantial behavioral detail: thresholds ($100k for large_move, $1M+ and a quarter change for hl_position), the fact that to_exchange is reported at any size, that USD values are best-effort, and that events include a destination label with its source. It also discloses the companion endpoint for the watch list itself, which is genuinely useful context beyond the annotations.

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 description is front-loaded with the core purpose and then structured as event types, return fields and filters, with every clause carrying information. It is dense and long, and a stray line break splits 'large share' mid-sentence, but no sentence is filler.

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 takes on the burden of explaining return values and does so: each event carries the sender's share of supply at list-add time, destination label and its source, amount, best-effort USD and an explorer link. Combined with the filter ranges and event definitions, an agent has everything needed to call this correctly.

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 description coverage is 100%, so a baseline of 3 applies, but the description adds real value: it supplies the 1-720 range for hours (the schema only says 'Look-back window in hours'), enumerates the valid type ids and chain values, and clarifies that type must be one of the values listed in the description. The one minor ambiguity is symbol — the schema specifies BASEUSDT contract form while the description calls it 'symbol (coin)'.

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 states a specific verb and resource plus its scope: 'Detective: what the watched large holders did', then narrows it precisely to private wallets holding a large share of a token's supply and Hyperliquid accounts with a large share of contract open interest. It enumerates the three event types (to_exchange, large_move, hl_position) with their triggering thresholds, which lets an agent separate it from broader whale/trader tools like get_hl_whales or get_top_traders.

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 context is implied by the filter list ('hours (1-720), chain (ethereum|solana|hyperliquid), type, symbol') and by the threshold definitions, which tell an agent what kinds of activity this tool surfaces. However, it never says when to prefer this over the sibling whale/trader tools, nor does it state exclusions or prerequisites for being on the watch list, so selection still requires inference.

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