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

The description adds valuable behavioral context beyond the annotations: it explains that default mode returns only the last 5 candles and derived metrics (token-saving), and that setting detail='full' or includeCandles=true returns the full candle array. It also notes the deprecated includeCandles parameter and the use of startTime for backtesting. The readOnlyHint annotation aligns with the read-only nature described, with no contradiction.

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 compact and efficient: a couple of sentences that front-load the core purpose, then immediately cover default behavior and how to opt into full data. It avoids filler and every sentence adds meaningful information about tool operation.

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?

Given there is no output schema, the description provides a reasonable overview of what is returned (summary metrics, last 5 candles, or full array). It also covers limit and startTime for historical data. It could be more explicit about the exact structure of the summary output, but it is sufficiently complete for a read-only data-fetching tool with good annotation coverage.

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% (all 7 parameters have descriptions), so baseline is 3. The description adds extra value by clarifying the default behavior of the 'detail' parameter (summary vs full) and the deprecation of 'includeCandles', as well as emphasizing the backtest use case for 'startTime'. This goes beyond mere schema repetition.

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 clearly states it returns native Binance OHLCV candlestick data ('Candlestick OHLCV native Binance'), and specifies it provides direction bias, swing highs/lows, and last price. It also distinguishes itself from Coinalyze as the source of truth, which helps differentiate from other data sources. This is a specific verb+resource with clear scope.

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?

The description mentions 'native Binance (source of truth, bukan Coinalyze)' which implies this is the preferred tool for Binance Futures data, and it discusses the default summary mode versus full mode for token efficiency. However, it does not explicitly contrast with sibling tools like binance_get_spot_klines or binance_get_continuous_klines, though the mention of 'Binance Futures' in the symbol parameter provides context. This is clear on when to use it but lacks explicit exclusions.

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