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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false). The description adds meaningful context beyond them: the pricing model (250/day free allowance, then $0.25 USDC on Base via x402), the no-account/no-API-key access model, and the ~1.9x inflation factor observed. The only gap is that the intended return contents ('the naive t, the date-cluster...') are cut off.

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 rationale is well front-loaded, but the body is a run-on where the pricing sentence is jammed mid-clause ('the date-cluster RUNS NOW: served from a daily free allowance...') and the example request is truncated. The core message survives, but the structure and truncation hurt readability.

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 two-parameter statistical tool with no output schema, the description should explain what comes back; instead the return-value clause is interrupted before listing the clustered statistic or any p-value/CI. Inputs, trigger conditions, and pricing are covered, but the output story is incomplete.

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 two required parameters at 100% schema coverage, the schema already carries the burden, and its 'descriptions' are merely truncated examples. The description adds a little meaning by phrasing the inputs as 'per-trade returns and their dates', implying they are paired observations, but adds no format or alignment detail beyond the schema examples.

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 specific computation (clustered t-statistic that corrects for date clustering), names the problem it addresses, and contrasts the naive vs. clustered result. It is clearly distinguishable from statistical siblings like abtest, multipletest, and deflatedsharpe, though it never names those alternatives.

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?

It gives an explicit when-to-use trigger — trades that are not independent, several in the same day, same regime, or a correlated basket — which is concrete and actionable. It stops short of naming a competing tool to use when trades ARE independent, so routing is implied rather than fully specified.

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