backtest_strategy

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

With no annotations provided, the description carries the full burden. It does disclose a key behavioral trait—cost of $0.5—and states the return type. However, it omits other important aspects such as whether this is a simulation (no actual trades), potential latency, data requirements, or any side effects. The cost disclosure adds value, but overall transparency is incomplete for a paid, compute-heavy operation.

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 two short sentences, immediately front-loaded with the purpose. Every word adds value: the action, the resource, the cost, and the return type. It is concise and well-structured with no fluff or repetition.

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 the tool's moderate complexity (5 params, 4 required, nested object, no output schema) and complete lack of annotations, the description is insufficient. It fails to explain what 'performance metrics and risk analysis' concretely include, how to handle the 'custom' strategy, or any constraints on dates/assets. An agent would struggle to know expected outputs or edge cases without additional context.

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?

The input schema already provides 100% parameter coverage, including descriptions, enums, and a nested object for custom parameters. The description adds no additional semantic meaning beyond the schema, so it meets the baseline but doesn't enhance understanding of how parameters interact or when custom parameters are required.

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 the tool's purpose with a specific verb ('Backtest') and resource ('a trading strategy against historical data'). This clearly distinguishes it from sibling tools like strategy_* (which generate signals) or screener_* (which screen assets), making the intention unmistakable.

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 provides no guidance on when to use this tool versus alternatives. It doesn't mention exclusions, prerequisites, or situations where other tools (e.g., strategy_momentum, indicator_*) would be more appropriate. The only contextual hint is the cost, but no 'use this when...' direction is given.

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