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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds meaningful operational context: a per-call price ($0.002 USDC via x402 on Solana), an equivalent HTTPS endpoint, and the conditional behavior that correlation matrices only appear with several named series. It does not cover failure modes or input size limits, keeping it below a 5.

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?

Front-loaded with purpose, then the metric inventory, then transactional details. It is dense but every clause carries information; the long metric list is justified because there is no output schema. The pricing/endpoint sentence is slightly tangential to a stats tool but still actionable.

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 and six parameters, the description effectively doubles as return-value documentation by listing every statistic returned (moments, quantiles, MAD, geometric/harmonic means, CI, outliers, histogram, correlations). Combined with input-format handling and the payment model, an agent has everything needed to call it correctly.

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 67% (only 'confidence' and 'percentiles' lack schema text), and the description compensates by naming percentile conventions, the t confidence interval, and histogram binning as numpy 'auto'. It also adds interpretation the schema lacks, such as null/'NA' handling for data and comma-separated field names for multi-field object arrays.

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?

States a specific verb and resource ('Descriptive statistics for one or many numeric series') and then enumerates the exact metric set produced, including named conventions (Excel SKEW/KURT, numpy/PERCENTILE.INC, Tukey outliers). An agent can immediately tell this apart from siblings like text_stats, csv_profile, hypothesis_test or regression_fit.

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 implies usage through its input description ('accepts numbers, numeric strings, nulls / "NA" or objects plus a field name') and by noting correlations only appear for several named series. However, it never says when to choose this over alternatives such as hypothesis_test, regression_fit, csv_profile or text_stats, and gives no exclusions or prerequisites beyond the payment note.

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