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

Annotations cover the safety profile (readOnly, idempotent), and the description adds genuinely non-obvious behavior: the tool returns x402 payment requirements and a URL rather than the data itself, costs $0.005, is backed by an 8-day-retention snapshot store, and fails without charging on bad input. That is exactly the kind of context annotations cannot convey.

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 paid-cost headline and the data scope, then constraints, then the sample link. Dense but every clause carries information; slightly packed with parentheticals that slow scanning.

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 usefully discloses cost, retention, error/no-charge semantics, payment-requirement return, and a free sample URL. What's missing is any hint of the response payload shape once payment is settled, which an agent planning a call would want to know.

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 50% — symbol is documented in-schema but hours is bare. The description compensates by stating the valid range and the default of 24, which the schema does not express (it only carries an example). It still doesn't say what hours means precisely (window ending now? aligned to snapshot cadence?), so not a 5.

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+resource: 'about-hourly open-interest history (coins, USD, mark, hourly funding) for one Hyperliquid main-dex perp'. It also names the data source (cryptofeed402 snapshots) and scopes to a single symbol, which cleanly separates it from get_funding_history or get_candles without the agent 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 useful preconditions (hours 1-192 default 24, paid $0.005, HIP-3 symbols and bad params error out with no charge) and explains why this exists ('Hyperliquid has no public OI history'). But it never routes the agent to or away from a sibling tool — there is no explicit 'use this instead of get_funding_history when...' guidance, leaving the choice to inference.

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