모의 심사(채점)

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states deterministic behavior (no randomness), maps to a rubric, and returns specific outputs. It also includes a caveat about reference use, which adds transparency beyond a simple functional description.

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 two sentences long, well-structured, and front-loaded with the core purpose. Every sentence provides meaningful information without unnecessary words or redundancy.

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?

Despite having no output schema, the description adequately explains the return values (total score, item scores, deduction reasons, etc.). It addresses the tool's complexity with 3 parameters (one nested object) and provides a caveat about reference use, making it complete for agent invocation.

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 the schema already documents all parameters and their types. The description adds marginal value by explaining that the tool maps to a rubric and returns scores, but it does not provide additional syntax or format details beyond what the schema offers. Baseline 3 is appropriate.

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 that the tool deterministically scores a business plan summary by mapping it to a rubric (no randomness). It specifies that it returns total score, item scores, deduction reasons, improvement points, and next edit suggestions, distinguishing it from sibling tools like 'plan_review' or 'draft_section'.

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 notes that the tool is for reference and may differ from the final evaluation ('참고용이며 운영기관 최종평가와 다를 수 있습니다'), but it does not explicitly state when to use this tool versus alternatives like 'check_eligibility' or 'plan_review'. The usage context is implied but lacks exclusions or explicit guidance.

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