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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered externally. The description adds only that z, percentile and p-value are produced, which duplicates the output schema; there is no mention of domain errors such as division when std_dev approaches the 0.001 minimum. Adds some context but nothing beyond structured fields.

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?

Three short sentences, front-loaded with the operation and its inputs, followed by usage and a cross-reference. The 'Returns z, percentile, p-value' sentence is largely redundant with the existing output schema, which is the only wasted space.

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 pure three-number calculator with complete schema coverage, a full annotation safety profile and an output schema, the description covers purpose, inputs, usage context and a discovery pointer. The remaining gap is the absence of disambiguation from calculate_percentile_rank and calculate_statistics.

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 each parameter already carries its own description ('Observed value', 'Population mean', 'Standard deviation'). The description restates those same three inputs without adding format, unit, or edge-case semantics (e.g. the std_dev minimum of 0.001), so the baseline of 3 applies.

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 names a specific verb+resource ('Compute z-score (standardized score) and percentile') and enumerates the three inputs, so the agent knows exactly what operation this performs. It stops short of distinguishing itself from overlapping siblings such as calculate_percentile_rank or calculate_statistics, which also touch standardized scores.

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 for statistics and outlier detection' gives a usage context, and the list_bundles pointer offers a discovery path, but there is no when-not guidance and no explicit routing away from the near-duplicate percentile/statistics calculators. Adequate but thin given how crowded the sibling set is.

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