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

Annotations already declare readOnlyHint/destructiveHint/idempotentHint, but the description adds the non-obvious 'why': each call is billed, so repeats are not free, which explains idempotentHint=false. It also discloses price, the free-tier allowance, the 10,000-number cap, and that failed calls are free — real value 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 output list is front-loaded and the example, limits, and pricing follow in a logical order. Slightly dense — the pricing/second sentence is long — but each sentence carries information an agent can act on.

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, the description fully compensates by enumerating every returned statistic and the interpolation method for percentiles. Combined with input format, size cap, and cost model, an agent has everything needed to call and interpret it.

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 100% for the single parameter, and the schema already documents the separator formats. The description adds the 10,000-number limit and a worked example, but omits the newline separator mentioned in the schema — marginal added meaning, so baseline 3.

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 opening clause names a specific verb (compute descriptive statistics) and a specific resource (a list of numbers), then enumerates the exact outputs (mean, median, variance, quartiles, percentiles). That makes it easy to distinguish from math_evaluate or text_stats by subject matter, though no sibling is named explicitly.

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?

'Use to summarise measurements, latencies, prices or scores without a spreadsheet' gives concrete, actionable usage context. It does not, however, state when to prefer a sibling such as math_evaluate (expressions) or text_stats (text corpora).

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