compare_strategies

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

Annotations already signal readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context not in annotations, notably that shorter periods cause rsi_pullback and triple_ema to contribute zero trades due to incomplete SMA200 warmup. It stops short of describing output structure or runtime characteristics, but the added caveat is genuinely valuable.

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 core purpose in a single sentence, followed by a clean, well-structured Args block. Each parameter entry earns its place by adding examples, defaults, or caveats rather than repeating schema content verbatim. There is no filler or redundancy.

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 adequately explains what the tool returns ('a ranked leaderboard'), documents all 4 parameters, and warns about the warmup limitation. The only gap is that the leaderboard's exact fields or ranking criteria are not specified, which would help an agent consume the result, but invocation is fully supported.

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%, so the description carries the full burden for parameter semantics. It compensates thoroughly: symbol is explained with examples, period lists all allowed values plus a trade-off, initial_capital states currency and default, and interval lists valid options. Every parameter is effectively documented beyond the bare schema.

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 action: 'Run all 9 strategies' and the specific result: 'return a ranked leaderboard.' It even enumerates the nine strategies, making the resource well-defined. It does not explicitly name sibling alternatives like backtest_strategy or walk_forward_backtest_strategy, so it lacks explicit sibling differentiation.

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 strong usage context, including valid period and interval values, defaults, and a concrete recommendation that period >= '1y' is needed for RSI Pullback and Triple EMA to complete SMA200 warmup. It does not explicitly state when to choose this tool over siblings, but the parameter guidance is clear and actionable.

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