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

No annotations are provided, so the description carries the entire behavioral burden. It only says 'Expression discarded,' which hints that the input is not store, but it does not explain what the result is, whether the call has side effects, whether it is a read-only check, or what error situations look like.

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 description consists of two short sentences with no fluff and the core 'Evaluate' verb appears first. It earns some credit for being compact, but the terseness contributes to ambiguity and omits operational details the agent needs.

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?

The tool has nine optional parameters, no output schema, and no annotations, so the description must provide strong orientation. It doesn't explain how to express `a+b`, what the evaluation returns, whether the expression is a required runtime concept outside the schema, or how to distinguish this from fetch-status, validate-json, and similar sibling tools.

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?

Although the input schema descriptions cover 100% of the parameters, the tool description adds no mapping between the described 'a+b' expression and any of the nine string fields (ref, url, city, feed, host, etc.). The expression concept has no representative parameter, so the description is off-center with the schema and doesn't help the agent choose which field to populate.

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 an operation ('Evaluate a+b style arithmetic') but it is disconnected from the actual input schema, which has no arithmetic expression parameter. 'Expression discarded' further muddles what the tool does, and the description does not differentiate this from sibling validators such as validate-json or yaml-ok.

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?

There is no guidance on when to use this tool instead of a sibling, and no prompt autofill about when to skip it either. The one-line description never mentions inputs such as query, url, or ref, so an agent cannot decide between calc-eval and closely related validation or normalization tools.

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