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

Annotations already establish this is a non-destructive read (readOnlyHint=true, destructiveHint=false), so the description's job is to disclose the simulation's assumptions — and it does: live rule engine, PancakeSwap fees, BNB Chain gas, fixed $100 sample, 4h candles, one-year window, plus a buy-and-hold benchmark. It omits anything about latency, rate limits, or that openWorldHint means the result depends on live market data, which keeps it off a 5.

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 rhetorical opening 'Would this simple strategy have made money over the last year?' frames the tool before the technical detail, and the entry-rule enumeration is dense but necessary. A few clauses (the dolphinamp.xyz/test reference) do not earn their space for an agent, but overall there is little waste.

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?

There is no output schema, and the description partially compensates by saying the result is compared with just holding the coin, which hints at the shape of the answer. It also fixes the ambiguous inputs (timeframe, capital, fee model) that would otherwise be unknowable. It does not say what metrics come back (return, drawdown, trade count), which is the remaining gap for a tool with no return-value schema.

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 60%, and the description compensates well for the undocumented `entry` enum by spelling out all four modes (dip, rsi, trend, momentum) and how `level` is interpreted in each. It also clarifies that target and stop are percentages measured from the entry. The allowed level/target/stop value sets live only in the schema, and `coin` is left unexplained, so it is good rather than exhaustive.

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+resource: it replays a preset entry strategy over the last year of Binance 4h candles with Dolphin's live rule engine, fees and gas on a $100 sample, and compares against buy-and-hold. That is far more specific than the name alone. It never names the closest sibling (backtest_rule) or explains how this preset-strategy test differs from a custom-rule backtest, so it stops short of a 5.

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 is only implied: the four entry presets with their allowed `level` values suggest this is the tool for quick, pre-built strategy checks, and 'Give a target and/or a stop' tells the agent how to complete a call. There is no explicit when-to-use versus backtest_rule or best_strategies, and no statement of what to do if the parameters are invalid.

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