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

With no annotations, the description carries the full behavioral burden and does disclose key behavior: the computed outputs, that interpretations come with assumptions, the optional tail direction, and the alpha default. It does not address edge cases like invalid inputs or missing data, but the core behavior is transparent.

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 a single dense, front-loaded paragraph with no filler; it states the purpose first, then the test menu and defaults. The compact brace syntax is efficient but somewhat dense, requiring careful parsing to map each test to its parameters.

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 17-parameter tool with no output schema and no annotations, the description covers test selection, most parameter groupings, defaults, and expected return content. It is not exhaustive—invalid input handling and exact return structure are absent—but it provides enough for an agent to invoke the common cases 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 description coverage is 0%, so the description must compensate, and it substantially does by binding parameters to specific tests, e.g., one-sample-t {data, mu0}, one-proportion-z {successes, n, p0}, and chi2-independence {table}. The main gaps are the ambiguous 'expected?' optional marker and the unspecified structure of 'table', so a few parameters remain under-specified.

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 opens with a specific action ('Run a significance test') and clearly lists the outputs: statistic, p-value, and plain-language interpretation with assumptions. The enumerated test menu (one-sample-t, two-sample-t, one-proportion-z, etc.) makes the tool's scope unmistakable and distinguishes it from estimation or descriptive sibling tools.

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 practical selection guidance by mapping hypothesis scenarios to concrete test names, and documents defaults for tail and alpha. However, it never explicitly states when to prefer hypothesis_test over siblings like confidence_interval or descriptive_stats, nor does it provide when-not conditions.

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