fpl_backtest_strategy

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

No annotations are present, so the description carries the full behavioral burden. It discloses two execution modes and the exact parameter combination needed to replicate the research candidate, which is meaningful. However, it does not describe what the backtest returns, whether it is read-only, what data prerequisites exist, or what failure modes might occur, leaving notable gaps.

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?

Two sentences earn their place: the first states the purpose and the two mode routes, the second gives a compact reproducible recipe. It is front-loaded with the core action and uses no filler or repetition, which is exemplary for a tool with 21 parameters.

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 complex 21-parameter tool with no output schema and no annotations, the description is not complete enough. It explains two modes and a recipe, but an agent still does not know what the backtest returns, whether one of the two modes is required, which combinations of optional parameters are valid, or what the results look like. The description is a helpful starting point, not a complete invocation guide.

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?

With only 10% schema description coverage, the description must compensate, and it partially does: it adds meaning to scenarios/scenarios_path, history_root, season, forecast_model, policy, and initial_squad_modes. But 21 parameters exist, and many (seed, objective, candidates, depths, beam widths, cocktail_config, etc.) get no semantic help from either the schema or the description, so compensation is incomplete.

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 with a specific verb+resource: 'Backtest and compare tunable strategies.' It clearly identifies the tool's core function and distinguishes it from sibling tools like fpl_recommend_moves or fpl_strategy_info by virtue of the backtesting action, but it never explicitly names or contrasts those siblings, so it stops short of full 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 gives explicit routing between two modes: use scenarios/scenarios_path for point-in-time replay versus history_root plus season for the Vaastav-format simulator. It also names a precise parameter recipe to reproduce the published 2,486-point candidate. It lacks explicit 'when not to use' guidance against sibling tools, but the intra-tool guidance is strong.

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