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

The description goes well beyond the readOnlyHint annotation by disclosing that the tool is paid, runs multiple statistical tests (DSR, permutation test, purged k-fold), optionally produces concentration/regime analysis, and does not retain inputs beyond a redacted audit hash. It also states the possible verdict categories, giving the agent a clear picture of expected behavior.

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, front-loaded with the verdict, and every major sentence carries useful information. It is somewhat long and packs several optional behaviors into flowing prose, but it remains readable and avoids redundancy.

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 complex 8-parameter tool with no output schema, the description covers inputs, methodology, verdict values, optional behavior, and privacy. The main gap is that it does not specify the exact response structure beyond the verdict labels and the 'concentration_and_regime' key.

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?

With 75% schema description coverage, the schema already documents most parameters. The description adds value by explaining how n_trials and trial_sharpes feed the Deflated Sharpe Ratio haircut, how the trade-row alternative uses fields like ret/pnl/net_bps, and how 'coin' and 'ts' trigger the optional concentration/regime outputs.

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 states a concrete verb ('Submit'), a specific target ('a strategy's realized returns or trade rows'), and a concrete output ('verdict: likely_real / borderline / overfit_or_noise'). It also differentiates itself by explicitly saying 'NOT the strategy itself,' which helps distinguish it from nearby sibling tools like prove or verify_proof.

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 clearly implies when to use it — when a backtest reality-check is needed — and warns against submitting the strategy itself rather than returns. However, it does not explicitly name alternatives or state when not to use this tool, which is a gap given the large sibling list including audit_agent_readiness and conformance_certify.

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