geometry.vector_cross

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

Annotations already declare readOnly and idempotent, so the safety profile is covered. The description adds meaningful context beyond them: computation is exact via Decimal rather than floating point, the result is a 3-element list, and operation order affects the sign. It does not discuss error behavior for malformed input, which keeps it below 5.

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?

Four short sentences, front-loaded with the core operation, then constraints. Each sentence contributes something (type, arity, ordering, 2D handling) with no filler.

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 two-parameter pure math tool with an output schema and read-only annotations, the description covers types, arity, ordering semantics, and the 2D edge case. Only input-validation failure behavior is left unspecified, a minor gap given the tool's simplicity.

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 0% (parameters are bare 'A' and 'B' arrays of strings), so the description carries the full burden. It does so well, specifying that each input must be exactly 3 elements of Decimal-typed strings, which prevents the common float/string-length mistakes.

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?

States a specific verb and resource ('3차원 벡터의 외적 a × b') plus the numeric mode (Decimal arithmetic). This clearly separates it from siblings such as geometry.vector_dot, geometry.vector_norm, and geometry.matrix_multiply.

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?

Gives real usage guidance: warns not to confuse a × b with b × a because the sign flips, and instructs padding z=0 for 2D inputs. It stops short of naming alternative tools (e.g., vector_dot for the scalar product), so it is strong but not exhaustive.

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