whatif

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

With no annotations, description carries the burden. It identifies the tool as a replay with overrides, implying no destructive side effects. However, it doesn't disclose computational cost, required permissions, or output behavior beyond the replay analogy.

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 concise sentences, front-loaded with purpose. Every sentence adds value with zero fluff. Efficient structure.

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 4 parameters (2 required, nested object) and no output schema, the description covers the core scenario well. References sibling 'replay_window' for shared behavior, but could add more about return format or performance implications. Still, adequately complete for the complexity.

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 has 0% description coverage. Description adds meaning for 'strategy' (strategy-name filter) and 'param_overrides' (required, exemplified), but doesn't clarify 'from_ts_ns' and 'to_ts_ns' beyond implicit reference to 'replay_window'. Partial improvement over 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?

Clearly states 'counterfactual replay' and positions it relative to 'replay_window'. Includes specific examples ('what if EMA period was 50 instead of 21') distinguishing the tool from siblings.

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?

Explicitly says 'same as replay_window plus a strategy-name filter and required param_overrides', giving clear context for use. Provides concrete examples ('show me the PnL if I had used a wider stop') but lacks explicit when-not-to-use guidance.

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