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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: no account or API key required, a 250-call daily free allowance, and a $0.31 USDC-on-Base x402 charge thereafter. It does not disclose computation traits (e.g., required sample size, rerandomization count), which keeps it out of 5 territory.

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 verbatim and then mangled into '…vs your own shuffled returns RUNS NOW:', which reads as a copy-paste artifact. Pricing and an inline JSON example are appended without structure, so the description is noisy rather than front-loaded; only the fact that it is short keeps this above 1.

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 one-parameter read-only tool with a high-coverage schema, the description covers access/payment and gives an example payload. What it omits is the output: with no output schema, the agent has no idea what comes back (a p-value, a verdict label, a distribution?) or what input constraints apply, so it is only marginally adequate.

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% for the single 'returns' parameter, so the schema already carries the burden. The description supplies a worked example request, which is mildly helpful, but it never explains what 'returns' means (per-period decimal returns? percentages?) or any constraints such as minimum series length. Baseline 3 applies.

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 a question ('Is this drawdown a broken strategy or a normal bad patch') rather than stating a specific verb+resource like 'test whether an observed drawdown is statistically significant against shuffled return series'. The 'vs your own shuffled returns' clause hints at the method, but the framing is sales copy-style and offers no differentiation from siblings such as deflatedsharpe, multipletest, or samplesize, which perform adjacent statistical checks.

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?

There is no statement of when to reach for this tool versus the many statistical siblings. The only usage-adjacent content is billing mechanics ('free allowance, then $0.31'), which tells the agent nothing about when the tool is the right choice or what inputs make it meaningful.

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