evaluate_expression

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description confirms it evaluates expressions but adds no new behavioral traits beyond the annotations. It is consistent, but the contribution beyond annotations is minimal.

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 a single dense paragraph with no wasted sentences. It front-loads the purpose and then efficiently lists supported features. Every sentence adds value, making it concise and well-structured.

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 complex tool with one parameter and no output schema, the description thoroughly covers expression syntax, functions, constants, and notation. However, it lacks mention of the return type (e.g., number) or error handling behavior, which would enhance completeness. Annotations cover safety aspects, so the description is still fairly complete.

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 has one parameter 'expression' with no description (0% coverage). The description compensates by detailing what the expression can contain: operators, functions, constants, parentheses, scientific notation, and an explicit usage tip ('2 * pi, not 2pi'). This adds significant semantic meaning beyond the bare schema.

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 clearly states 'Evaluate a mathematical expression' and declares it the 'PRIMARY tool for ALL math', which distinguishes it from siblings like sin, cos, etc. It lists supported operators, functions, and constants, making the purpose specific and unambiguous.

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 says 'PRIMARY tool for ALL math', implying use for general expressions, but does not explicitly mention when not to use this tool or how it compares to sibling tools (e.g., sin, cos). Given the many sibling math function tools, more explicit guidance on when to use evaluate_expression versus individual functions would improve this dimension.

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