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

No annotations are provided, so the description must carry the full behavioral disclosure burden. The only behavioral trait disclosed is 'Expression discarded', which addresses data retention but not whether evaluation is read-only, what the return value is, how errors are handled, or what happens with the other nine schema parameters.

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 is just two short sentences with no filler: the purpose and the discard behavior are front-loaded. However, the extreme brevity contributes to the lack of necessary input and usage details.

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 tool with no annotations, no output schema, nine parameters, and many siblings, this definition is far from complete. It does not explain how to supply an expression, what result is returned, when to use it, or how the other parameters relate, so an agent cannot call it correctly from the provided 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 descriptions cover all nine parameters, so the baseline is 3, but the description introduces an 'expression' input that has no corresponding property. Because additionalProperties is false, an agent cannot determine how to pass 'a+b' to this tool, making the description actively confusing rather than additive.

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 concrete operation, 'Evaluate a+b style arithmetic', which suggests a calculator tool, but it does not map to any input field: none of the nine schema properties (ref, url, city, feed, host, json, path, zone, query) represents an arithmetic expression, and additionalProperties is false. This makes the stated purpose effectively unusable and inconsistent with the schema.

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 versus any of the many sibling tools, such as domain-shape, validate-json, timezone, or normalize-url. The description provides no context, prerequisites, alternatives, or exclusions, and all parameters are optional, so an agent has no signal for selecting this tool.

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