Audit a backtest

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

Beyond annotations, the description discloses meaningful behavioral details: each check consumes one validation, each check produces its own receipt, the tool does not grade the strategy, and thresholds are not admission or forecasts. This materially changes how an agent should treat the output and complements the sparse annotations.

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 dense but every sentence earns its place: outputs, file usage, relationship to validate tools, validation cost, and interpretive caveats are all covered with no redundant phrasing. Key operational information about file usage is front-loaded.

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 11 parameters breeding a complex audit workflowchers, the description covers the purpose, the checks performed, the file-based input alternative, the receipt behavior, the validation cost, and the non-grading caveat. Since there is no output schema, the description provides enough return-shape information through test coverage of 'each check' and 'own receipt' for an agent to invoke and interpret the tool correctly.

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 100%, so most parameter meaning already lives in the input schema. The description adds some practical nuance around returns_file and variants, but it does not add syntax or semantics beyond what the schema already provides. Baseline 3 is appropriate.

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 uses a specific verb ('Audit'), a specific resource ('one strategy's return series'), and enumerates the concrete outputs: deflated Sharpe, minimum track record length, and probability of backtest overfitting. It also distinguishes itself from the validate_* siblings by framing those as individual checks and the audit as their side-by-side combination.

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 says when to use the tool: to audit one strategy in one call, and it gives operational guidance to point returns_file at a CSV/JSON instead of copying long series. It references the matching validate_ tools and clarifies the audit 'does not grade the strategy,' making the intended alternative relationship inferable, though it does not explicitly say 'use validate_deflated_sharpe when you only need one check.'

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