evaluate

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

In the absence of annotations, the description discloses key behaviors: supported numeric domains (real/complex), configurable angle modes (rad/deg/grad), complex output forms (rectangular/polar), and engineering symbol handling. It also gives concrete examples that demonstrate expected behavior. However, it does not describe error handling, return value format, or variable interpolation semantics, leaving some edge-case ambiguity.

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 tightly structured with labeled sections (When, Not for, Params, Example) and front-loads the purpose. Every sentence contributes value, and the examples are concise but illustrative. The text is dense without being verbose, making it easy to scan.

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 the tool's moderate complexity and the presence of an output schema, the description covers the fundamental aspects: usage scope, exclusions, parameter details, and worked examples. Minor gaps remain around variable interpolation and complex_form output representation, but these are niche and partially mitigated by the output schema.

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?

With 0% schema description coverage, the description compensates by enumerating all five parameters with types, defaults, and valid values (e.g., angle_mode=rad|deg|grad, complex_form=rectangular|polar, variables={name:float}, eng_symbols=bool). It even provides examples that illustrate parameter usage. This meaningfully enriches the bare schema, though it could better explain how variables are referenced in expressions and the precise effect of complex_form on the output.

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 opens with 'When: ordinary infix maths (real/complex), trig, powers, eng suffixes, angle suffixes, polar ∠,' which clearly specifies the tool as a mathematical expression evaluator with particular feature domains. The 'Not for' list explicitly excludes matrices, stats lists, BASE-N, TVM, and unit conversion tables, which distinguishes it from sibling tools and sharpens its purpose.

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 provides both positive ('When:') and negative ('Not for:') usage guidance. The exclusions map to specific sibling tools (e.g., matrix_op, stats_1var, base_convert, finance_tvm, convert_unit), effectively directing the agent to alternative tools when the input does not fit the evaluator's scope. This is explicit and actionable.

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