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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, closed-world), and the description adds genuinely new operational context: 32 KB payload limit, 60 RPM rate limit, auth options (?demo=true or L402 at 60 sats), and HTTP 400 on invalid input. That is exactly the kind of constraint info the annotations cannot carry.

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 core purpose and the routing rule are front-loaded in the first two clauses, with operational details trailing in a compact parenthetical. It is dense but largely waste-free; the parenthetical is heavily compressed to the point of being cryptic, which costs a point.

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 an output schema present, return values need not be re-explained, and the description still covers test coverage, inputs, auth, rate limits, size limits, and error behavior. Nothing an agent needs to invoke this tool correctly is missing.

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%, so the schema already explains control_json, treatment_json, and the significance_level enum with its default, giving a baseline of 3. The description adds only the ambiguous claim that "'treatment_json' defaults to 'standard'", which actually conflicts with the schema marking treatment_json as required and does not clarify parameter semantics.

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 precise verb and resource ('Computes Welch's two-sample t-test or two-proportion z-test') and enumerates the exact outputs (two-tailed p-values, Cohen's d, relative lift %, Bayesian P(Treatment > Control)). It also names the sibling it is not, evaluate_deterministic_math, so an agent can route without opening either 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?

Gives an explicit use case ('whether a prompt change, model benchmark, or A/B experiment produced a statistically significant improvement') and an explicit exclusion with a named alternative ('for evaluating single algebraic formulas or NPV/IRR cashflows, use evaluate_deterministic_math instead'). Both the when and the when-not are stated.

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