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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds real context: result.penalty is always an estimate, LG U+ subsidy is a formula reference that may differ from the final bill, invalid combinations return errors, and no auth or account lookup is performed. This meaningfully exceeds the annotation set, though it stops short of describing scaling or edge-case behavior.

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?

Seven sentences, but front-loaded with purpose and each subsequent sentence carries a distinct constraint (input exclusivity, per-type requirements, output unit/estimate caveat, auth scope, evidence route, error policy). Dense but not padded; it could be slightly tightened but no sentence is wasted.

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?

With an output schema present, the description need not explain returns, yet it still flags the key output field and its estimated nature. Inputs, conditionality, error handling, auth scope, and the evidence sibling are all covered, so an agent has everything required to call it correctly.

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%, so 3 is the baseline, but the description synthesizes cross-parameter constraints (exactly one of the elapsed pair; per-penaltyType required fields; 24-month-only for public_subsidy) into a single rule set an agent can apply before reading the schema. Much of this is also in the schema text, so it does not reach 5.

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 precise verb+resource+scope: calculates SKT/KT/LG U+ contract penalty reference values. It also delimits what the tool is NOT ('무인증·읽기 전용이며 통신사 개인계정 조회·해지는 하지 않습니다'), so an agent can separate it from account-management siblings and from the other calculate_* tools.

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?

Explicit conditional rules: provide exactly one of elapsedMonths/elapsedDays; selective_contract needs accumulatedDiscount; public_subsidy needs receivedSubsidy and a 24-month contract. It routes elsewhere for evidence (get_calculation_evidence) and forbids guessing on error ('입력을 추측해 재호출하지 마세요'), which is clear when/when-not guidance.

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