verify_execution

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

With annotations declaring readOnly, idempotent, and non-destructive, the description adds rich behavioral detail: it reconstructs P&L via a formula, binds to a data hash, composes a Deflated Sharpe, and catches mismatches. It also discloses limitations ('NOT that the data is the real market', 'NOT that positions weren't overfit') and clearly states it does not run strategy code.

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 long and uses all-caps headers, but every sentence earns its place, explaining the algorithm, the honest scope, and exclusions. It is front-loaded with the core idea. Slightly verbose but appropriate for a complex tool.

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?

The description thoroughly explains the verification logic and limitations, but it does not state the return value format or behavior on mismatch (e.g., what the tool returns when verification fails). Since there is no output schema, this is a notable gap for an agent to fully understand invocation results.

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%, so baseline is 3, but the description significantly enhances parameter meaning by providing the exact formula (r_t = pos_{t-1}·assetret_t − costs), explaining how positions and asset returns interact, and clarifying the roles of reported_sharpe, n_trials, and canonical_hash. This goes well beyond the schema's field-level descriptions.

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 the tool re-derives a Sharpe ratio from positions and asset returns, recomputes it from an explicit formula, and checks it against the claimed value. It distinguishes itself from siblings by emphasizing 'instead of trusting a reported Sharpe' and by honestly scoping what it proves vs. does not prove (data authenticity, overfitting).

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 gives clear context: it is used when you want to verify a Sharpe claim from decisions-on-committed-data, and explicitly says it does not run strategy code or prove data is real market (suggesting canonical_hash for that). It does not name specific sibling tools but enough exclusions and scope to guide selection.

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