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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful operational context beyond that: a daily free allowance (250 remaining), a $0.31 USDC payment via x402 on Base, and no account or API key required. This billing/auth disclosure is exactly the kind of value structured fields cannot carry.

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 opening sentence is duplicated word-for-word, and the run-together text 'the search you ran RUNS NOW' merges two unrelated thoughts with no punctuation or break. The pricing paragraph is front-loaded as a wall of text rather than separated from the conceptual explanation.

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 no output schema, the description carries the burden of explaining results, yet it never says whether the tool returns a deflated Sharpe value, a p-value, or a verdict. It does cover cost, auth and a sample input, which makes it usable, but an agent still cannot anticipate the response shape.

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% and the two parameters (returns, n_trials) already carry example values in the schema. The description repeats the same example request but adds no new meaning about units, minimum series length, or how n_trials should be counted. Baseline 3 applies when the schema does the work.

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 frames the tool as answering 'Is this Sharpe real, or the best of N tries?' adjusted for the number of trials, which conveys the concept of a deflated Sharpe ratio. However, the verb+resource statement is implicit and the key sentence is duplicated verbatim, so it never states plainly what it computes or returns. It also does not distinguish itself from siblings like multipletest or check_eval_selection.

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 no when-to-use or when-not-to-use guidance and never names an alternative among the many statistics siblings. The only conditional content is commercial (free allowance exhausted, then paid), not about selecting this tool over others.

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