양도소득세 예상 계산

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

Annotations declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false. The description adds behavioral context: it rejects unsupported cases, is deterministic, and provides estimates. No contradictions.

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 three sentences with purpose, constraints, and disclaimer. It is front-loaded and efficient. Minor bilingual mix (English/Korean) could be streamlined but does not hinder clarity.

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?

The description covers tool behavior and limitations but lacks output schema details. It mentions estimates for tax and local income tax but no info on return structure. Given nested input complexity, output specification would enhance completeness.

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 100% with detailed types and descriptions. The description adds only that the input must be 'complete, validated case,' which is already implied by the schema's required fields and descriptions. No extra parameter-level detail beyond 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 the tool 'deterministically estimates Korean real-estate capital gains tax and local income tax from a complete, validated case,' specifying the verb (estimates), resource (tax), and scope. It distinguishes from siblings: list_supported_capital_gains_scenarios and validate_capital_gains_case are different functions.

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 lists rejected cases (multiple transfers, inheritance/gift) and notes results are estimates, providing guidance on when not to use. It implies use for complete validated cases but lacks explicit comparison with siblings.

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