core.sub

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

Goes beyond the annotations by disclosing the 50-significant-digit working precision, the absence of rounding, and the input-string normalization requirement — real behavioral constraints an agent cannot infer from readOnlyHint/idempotentHint. It does not describe error behavior (e.g., what happens on malformed input), which keeps it short of a 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, purpose front-loaded, with the operand-order caveat placed last where it is most actionable. The clause noting the return is a 'result' string is largely redundant given an output schema exists.

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?

Annotations cover the safety profile and an output schema covers the return value, so the description only needs to add precision, rounding, and input-format constraints — which it does. The only real gap is the undocumented trace_level parameter.

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%, so the description carries the burden; it explains a and b substantively (digit strings without commas/units/spaces) and clarifies directionality (a minus b). The third parameter, trace_level, is never mentioned, leaving one parameter undocumented in both schema and description.

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 ('Decimal 정밀 뺄셈 a - b') and pins the operand order, which cleanly separates it from siblings core.add, core.mul and core.div. An agent can identify the operation without opening the schema.

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?

Offers operational guidance in the form of input-format rules (no commas, units, or spaces) and an explicit warning about operand order. However, it never names an alternative (e.g., core.add, core.calc) or states when not to use this tool, so routing guidance is only implied.

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