getPremiumIndexPriceKline

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

Annotations already mark the operation as readOnly and openWorld, and the description adds meaningful behavioral details: each kline entry is a 5-element array, data is returned in reverse chronological order, supported products are USDT/USDC perpetuals, and no authentication is required. It also notes the typical small decimal magnitude of premium index values. No contradiction with 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 well-structured and front-loaded, with the key definition in the first sentence and useful bullet lists. However, 'Data is returned in reverse chronological order (most recent first)' appears twice, and the Agent hint duplicates the premium-index definition and sibling routing already stated earlier.

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?

For a read-only kline endpoint with no output schema, it provides the return entry shape, ordering, supported products, authentication requirement, and clear sibling routing. The main gap is that start/end/limit timestamp semantics are left unexplained, so an agent must infer units and optionality.

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 0%, and the description does not explain symbol, interval, start, end, limit, or category beyond their names and enums. It only contextualizes the endpoint; the burden of parameter meaning is left entirely to the schema, which has no descriptions.

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 first sentence names a specific verb ('Query'), a precise resource ('historical premium index price klines'), and explains the premium index as the basis between mark price and index price for USDT/USDC perpetuals. It explicitly routes away from sibling kline endpoints, so it is distinguishable from getMarketKline, getMarkPriceKline, and getIndexPriceKline.

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 lists concrete use cases ('Analyze historical funding rate basis', 'Research the relationship...', 'Build charts...'), then gives an explicit exclusion: 'Do not use this endpoint for trading/mark/index price candles — use the respective kline endpoints.' The agent hint also names the alternative tools directly.

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