walk_forward

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

With no annotations, the description carries the full burden, but it only discloses that the tool executes a sequence of official tester runs. It does not mention long execution time, side effects, required setup, failure modes, or how IS/OOS windows are scheduled.

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 one compact, front-loaded sentence with no filler. It sacrifices completeness but remains clean and easily parsed.

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 14 parameters, no output schema, and no annotations, a single conceptual sentence is insufficient. An agent would not know what results to expect, what inputs are needed beyond the obvious, or how the walk-forward windows relate to the date parameters.

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 must compensate for the 14 parameters, but it only hints at is_days/oos_days through 'IS/OOS windows.' Required params like strategy, symbol, timeframe, and dates are not connected to usage, and optional params like model, inputs, deposit, and step_days are entirely unexplained.

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 identifies walk_forward as a walk-forward procedure composed of official tester runs with IS/OOS windows, which is a specific concept distinct from a plain single backtest. It lacks an explicit verb and doesn't name a sibling, but the core purpose is recognizable.

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?

There is no guidance about when to use this tool instead of run_backtest, run_batch, or other siblings. The description only defines what walk-forward is, not the conditions or prerequisites for choosing it.

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