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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered externally. The description adds genuinely new behavior context by disclosing the cost (1 credit) and the bounded operator set. It says nothing about error handling for invalid expressions or what a 'summary statistics' result contains.

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?

A single front-loaded sentence with the capability list inline and the cost in parentheses — no wasted wording. The compactness slightly hurts clarity, since 'summary statistics' is never defined, but the structure is efficient.

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 two-mode calculator with zero required parameters, the definition should disambiguate the modes and specify what statistics are produced (mean, median, count, etc.). It covers the operator surface well but leaves the statistics side and mode-to-parameter mapping underspecified, which is a real gap for a no-output-schema tool.

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 baseline is 3; the schema labels the two parameters, albeit with thin text ('string', 'array or comma list of numbers'). The description adds the operator vocabulary and mentions both input shapes but never explicitly ties 'expression' to the expression field and 'list of numbers' to the values field, leaving that mapping to inference.

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 gives a specific verb ('Evaluate') plus an explicit enumeration of supported operators and functions (+, sqrt, ln, min, max, pi), so an agent knows exactly the computation domain. It does not name any sibling, but no sibling (text_stats, convert_units, format_money) overlaps meaningfully, so differentiation is implicit rather than stated.

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?

Two operating modes are implied — a single expression versus statistics over a list of numbers — which hints at when each input should be used. However, it never states which parameter maps to which mode, and offers no exclusions or alternative tools for related needs.

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