replay_window

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

States read-only (sandbox-only mutations) and explains that the engine side decides the exact meaning of replay, mentioning tape primitives and SimulatedExecutor. With no annotations, this provides essential behavioral context beyond the schema.

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?

Three sentences, no wasted words. Front-loads the action and immediately provides usage examples. Efficient and clear.

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?

Covers purpose, behavior, and use cases adequately, but lacks detailed parameter explanations. With no output schema and four parameters, the description could provide more guidance on how to use each parameter.

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 coverage is 25% (only param_overrides has a description). The description hints at time window (from_ts_ns, to_ts_ns) but does not explain strategy or param_overrides. It adds some context but insufficient to compensate for low schema coverage.

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 it runs a sandbox replay over a time window, with specific use cases like 'replay the last hour'. This distinguishes it from general run_backtest by emphasizing sandbox-only mutations. However, it does not explicitly differentiate from all sibling tools.

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?

Provides explicit use examples (replay the last hour, rerun period in sandbox) and notes read-only behavior. Lacks explicit when-not-to-use comparisons to siblings like run_backtest, but the context is sufficiently clear for an agent to decide.

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