run_backtest

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

With no annotations, the description discloses that it returns a chart and metrics, and that the content text includes equity/drawdown JSON, with chartDetail controlling sampling. It also notes it handles data acquisition and calculation automatically ('unique implementation unnecessary'). However, it doesn't explicitly state it performs a read-only simulation with no real orders, which is a minor gap given the backtest context.

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 front-loaded with the tool's purpose and uses bullet-like lines for strategy, period, timeframe, and output details. Each sentence provides distinct information (strategy list, period options, timeframe, output metrics, JSON details, chartDetail sampling), with no fluff. The structure makes it easy to scan.

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 tool with 12 parameters and a nested strategy object, the description covers the core options and return details (metrics, chart, JSON). It explains chartDetail's sampling and mentions output format. It doesn't explain all parameters (e.g., fee_bp, outputDir constraints) but the schema covers those, so the description complements the structured data well.

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%, so the baseline is 3. The description reiterates the strategy enums, period options, and timeframe, and adds nuance about chartDetail sampling, but it largely overlaps with the schema's already-detailed parameter descriptions (e.g., precedence of start_date/end_date over period is in both). It adds little beyond what the schema already states.

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 opens by calling it a 'general-purpose backtest' with strategy names, and states it 'executes data acquisition through calculation to chart drawing in one go' – a specific verb and resource. It clearly distinguishes itself from sibling analysis tools by being the only backtesting tool, listing strategies (sma_cross, rsi, etc.) and output metrics (P&L, win rate, max DD, Sharpe).

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 implies when to use this tool by calling it 'general-purpose' and noting 'no need for custom implementation,' but it never explicitly contrasts it with sibling tools or states when not to use it. There are no exclusions or alternative routing. It could be clearer that this is the go-to backtest tool and that other analysis tools are for separate snapshots.

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