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

Annotations already declare read-only, idempotent, non-destructive behavior, but the description adds substantial extra context: it is FREE, it never raises protocol errors, it returns a structured {"error": ...} on invalid input, and retries are safe after correction. These are exactly the operational details an agent needs beyond the annotations.

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 purpose is front-loaded, followed by usage constraints, an example, and error behavior. The example output is somewhat detailed, but every section contributes useful information; no sentence is clearly redundant.

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?

Even though an output schema exists, the description still provides an example output shape and error semantics. Combined with the annotations covering safety and the schema covering all parameters, the definition is complete for correct invocation.

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 all four parameters are documented with types and bounds, so the baseline is 3. The description adds a concrete example input showing typical magnitudes (120/2400 and 156/2380), but it does not add new semantic constraints beyond what the schema already states.

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 verb and resource: 'Run a two-proportion A/B significance test with a plain-language verdict.' This distinguishes it clearly from the sibling tools (cohort_retention, correlation, csv_profile, forecast_trend, funnel_report, growth_rates), none of which perform hypothesis testing. An agent can identify the operation without opening the schema.

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 explicit positive and negative conditions: 'Use when exactly two variants each have a trial count and a conversion count. Not for continuous outcomes such as revenue per user, and not for three or more variants.' However, it does not name a sibling alternative for the excluded cases, so routing is slightly less complete than a 5.

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