reconcile_backtest

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

Annotations declare readOnlyHint, idempotentHint, destructiveHint false, and the description adds transparency about the statistical test (Mertens/Lo SE), the classification output (HELD/DECAYED/BROKEN), and the optional 'forward_check' receipt kind. This goes well beyond the 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 about 3 sentences, front-loaded with a question, and each sentence contributes: the core question, the inputs and outputs, and the receipt capability. Slightly verbose but not wasteful.

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?

With output schema present and annotations, the description covers the use case, the input contract, the decision categories, and the receipt aspect. It lacks explicit error handling or prerequisites, but overall it's sufficiently complete for a 4.

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 100%. The description adds conceptual meaning to claimed_sr and realized_returns (the promised Sharpe vs live returns) and mentions periods_per_year implicitly through 'per-period'. It doesn't add syntax details but reinforces the purpose of the main parameters.

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 ('reconcile') and clearly identifies the resource: comparing a backtest's claimed Sharpe against live returns. It distinguishes from siblings like verify_backtest by focusing on live return consistency, not backtest verification. The metaphor 'accountability oracle' adds clarity.

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 explains the exact input scenario: feed claimed per-period Sharpe and realized live returns. It implies the tool is for post-backtest accountability and is receipt-able, but doesn't explicitly state when not to use it or name alternatives. Clear context, no exclusions.

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