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

With no annotations present, the description carries the full burden of behavioral disclosure. It does disclose that the expression is discarded, which is a useful data-retention hint, but it does not say whether a result is returned, what side effects occur, or what 'discarded' means operationally. This is insufficient for a tool with no annotation safety profile.

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 only two short sentences with no filler, and the main verb is front-loaded. The second sentence does communicate a behavioral trait, so it earns its place. It is concise and scannable, though its brevity contributes to the ambiguity.

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?

Given no annotations, no output schema, and a mismatched input schema, the description leaves out critical operational information. An agent cannot determine how to supply the expression, what the tool returns, or when it should be selected. The 'discarded' note is a thin gesture toward completeness but does not resolve the core mystery.

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 individually documents its parameters well, so those entries would normally carry the semantic load. However, the description's core concept—an arithmetic expression—has no corresponding property in the schema, and the description adds no meaning to the listed parameters. An agent cannot tell which field, if any, should contain 'a' and 'b'.

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 action ('Evaluate a+b style arithmetic'), which is more than a tautology, but the second sentence ('Expression discarded.') undermines the purpose by suggesting the input produces no result. The input schema contains no expression parameter at all, so the stated purpose does not match the actual invocation surface. Overall the intent is ambiguous and not clearly differentiated from the many sibling shape-check 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 description gives no guidance on when to use calc-eval versus alternatives like validate-json or domain-shape. There are no prerequisites, exclusions, or examples. The 'a+b style' phrase is the only contextual hint, but it is not actionable without an expression parameter.

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