문제 → 개념

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and the description only needs to add lookup semantics. It confirms the tool resolves each item to a concept, but says nothing about partial resolution, unknown IDs, or result ordering — behavior an agent would want to know about a batch resolver.

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?

A single sentence with the resource and its accepted formats front-loaded; every clause carries information and nothing is padding.

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 one-parameter, no-output-schema tool, the input side is well covered but the return shape is never described — whether concepts come back parallel to the input list, as a dictionary keyed by item, or with unresolved items flagged. That missing mapping is the main completeness gap.

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 must carry parameter meaning, and it does the essential part by enumerating the accepted string formats for `items`. It does not mention that the array is capped at 30 entries or whether mixed formats may be combined in one call, so the compensation is strong but incomplete.

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?

Names a concrete verb+resource pair (returns the concept each exam item asks about) and gives three concrete input formats ('056', '모의1-22', '예시06') that make the item→concept mapping unmistakable. It does not explicitly contrast itself with search_concepts or get_concept, so the sibling differentiation is only implicit.

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?

Usage is implied by the input formats shown: you call it when you have exam item IDs and need the underlying concepts. There is no explicit 'use this instead of X when...' guidance and no statement about what to do with items that don't resolve, leaving the agent to infer routing.

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