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

'Expression discarded' does disclose that evaluation leaves no persistent state, which is a useful behavioral trait beyond the schema. However, with no annotations and no output schema, the description must also disclose what is returned, what inputs are accepted, and what failure looks like; it does none of that.

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 text is very short and front-loaded, which is structurally good. But this is under-specification rather than efficient completeness: the brevity hides the fatal omission of how an expression is provided to the tool.

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 annotations, no output schema, and seven schema parameters that have no apparent relationship to arithmetic, the description is far too incomplete for an agent to call this tool correctly. The core evaluation behavior is mentioned but cannot be operationalized from the available information.

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?

The schema documents seven unrelated parameters—ref, url, city, feed, host, json, path—and the description never identifies which one carries the arithmetic expression. Since there is no 'expression' field at all, the description not only fails to add semantic value but actively conflicts with what the schema shows.

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 says 'Evaluate a+b style arithmetic,' which names a verb and a resource, but it nearly restates the tool name and never explains how the expression is supplied. Because the input schema has no 'expression' parameter, the stated purpose cannot be mapped to an invocation, making it effectively misleading in context.

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 about when to use calc-eval over any alternative or when not to use it. The only usage hint is 'a+b style' syntax, but it is not connected to any request field, so an agent cannot infer valid input composition.

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