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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Expression discarded' communicates that the input is not retained, but the description does not say whether the evaluation result is returned, how invalid expressions are handled, or whether the operation is purely local and side-effect free.

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?

Two short sentences with no filler. The first sentence states the action and the second provides a behavioral note about the input. Every word earns its place, and the key information is front-loaded.

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 input schema is broad and heterogeneous, but the description only addresses the expression aspect and not the return value or error behavior. There is no output schema, so the description should clarify what an agent can expect after evaluation; 'Expression discarded' leaves this ambiguous.

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 input schema already provides descriptions for all parameters, including 'expr' as an 'Arithmetic expression like a+b to evaluate.' The description adds little beyond that, though it does reinforce the intended expression format. With high schema coverage, a baseline score of 3 is appropriate.

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 states a clear verb and resource: 'Evaluate a+b style arithmetic.' This makes it obvious the tool performs arithmetic evaluation rather than a URL, JSON, or file check. It does not explicitly name or contrast siblings, but the arithmetic scope is distinctive enough among the sibling tools.

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?

The usage context is implied: the tool should be used when arithmetic evaluation is needed. However, there is no explicit guidance about when not to use it or how it relates to sibling tools like validate-json, normalize-url, or web-fetch.

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