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

With no annotations, the description carries the full burden, but it only says 'Expression discarded' without explaining side effects, errors, or execution behavior. It does not clarify that the tool is read-only, stateless, or what happens with the supplied 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 short and front-loaded, but it is under-specified and internally inconsistent: the second sentence 'Expression discarded' conflicts with the stated purpose. The long, irrelevant parameter list makes the tool feel cluttered despite the concise description.

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 description does not explain the expected expression format, how to supply it, or what result the caller should expect. Given that the schema contains nine optional unrelated parameters and no output schema, the description leaves the tool essentially unusable.

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 schema has 100% description coverage, every parameter description (e.g., 'Git ref name', 'HTTPS URL to normalize or cite', 'File path to check') is unrelated to evaluating arithmetic. The descriptions actively mislead an agent and there is no parameter for the expression the tool claims to evaluate.

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 opening phrase 'Evaluate a+b style arithmetic' names a specific verb and resource, making the tool's intent recognizable. However, 'Expression discarded' is confusing and the input schema contains no expression field, which weakens an otherwise clear purpose statement.

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 description gives no guidance on when to use calc-eval versus any sibling tool, and it never explains what expression should be passed in. The sibling list contains many other evaluators/checkers, but no selection criteria are provided.

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