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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety bar is mostly covered. The description still adds real value beyond them: a privacy/data-minimization guarantee (only symbols and coarse PnL direction sent, no sizes or values), an auth requirement (api:read), and the coverage.uncoveredInstrumentIds signal for empty results.

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-loaded with the answer to 'what does this return,' followed by how to call it and privacy details. Dense but every sentence carries information; the parenthetical auth note and coverage field could be trimmed slightly.

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 steps up by describing the three feed item types and the coverage.uncoveredInstrumentIds escape hatch, which is exactly what an agent needs to interpret empty results. It stops short of explaining what the limit parameter caps or how items are ordered.

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?

Adds genuine meaning beyond the schema: the omit-both-to-derive behavior is spelled out, holdings/watchlist semantics are contrasted ('hold' vs 'watch but do not hold'), and ticker format is specified with an example (NVDA). limit and window are left entirely to the schema, which covers window's default but not limit's intent.

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 ('what changed' feed) and enumerates exactly what composes it: symbol-tagged news with model-written digests, notable price moves, upcoming earnings. The scoping to instruments the API-key user holds or watches separates it from get_news_feed and get_watchlist.

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?

Explicitly describes two calling modes: no arguments derives holdings from open Hyperliquid positions, while passing holdings/watchlist controls coverage. It does not name the sibling alternatives (get_news_feed, get_tracking_updates, get_holdings) it should be preferred over, so the agent must infer the boundary.

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