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

There are no annotations, so the description must disclose behavior, but it only says 'Expression discarded.' It doesn't say whether the evaluation result is returned, whether the tool has side effects, what input forms are valid, or how failures surface. The bare stateless note is insufficient for a computation tool.

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 two sentences are front-loaded with the purpose and contain no filler. However, the second sentence 'Expression discarded' is cryptic and the description is far too terse for a tool with nine parameters and no annotations; it is under-specified more than cleanly concise.

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 nine parameters, no annotations, and no output schema, the description should explain how to invoke the tool and what a caller will receive. It does neither, and the disconnect between the stated expression behavior and the actual schema leaves the agent without enough context to call calc-eval reliably.

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?

Schema coverage is 100%, raising the baseline, but the description adds no mapping from its 'a+b expression' to any of the nine properties. Worse, it claims an expression is discarded while no parameter named expression exists, leaving the agent to guess which field (ref, url, city, query, etc.) is the calculator input.

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 specific operation, evaluating a+b arithmetic, so it is not a complete tautology. But it never connects that operation to any of the nine input properties—there is no 'expression' field—so an agent cannot tell what it should pass. It also doesn't differentiate itself from sibling shape/check tools beyond the verb 'evaluate'.

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?

No guidance is given about when to use calc-eval versus alternatives such as validate-json, domain-shape, or search-query-len. The phrase 'Expression discarded' hints at statelessness but does not state conditions, exclusions, or replacement tools.

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