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

With no annotations present, the description carries the full behavioral burden and does disclose the core trait: the tool aggressively filters results, excluding non-official, expired, estimated, or incomplete conditions, so an agent learns it will never return partial or unverified data. It does not, however, disclose return format, ordering, pagination, or failure behavior, leaving part of the burden unmet given zero annotation coverage.

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 dense Korean sentence with no filler; every clause adds a distinct criterion (verified status, remaining validity, no estimates/omissions, 24-month TCO). It could arguably be split for readability, but there is nothing to remove.

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 fully defines the tool's result domain, which is the core information an agent needs to select it. It falls short on call-shaping details—parameter meanings, what returned objects look like (no output schema exists), and how limit interacts with the strict filter—leaving moderate ambiguity before invoking.

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 description coverage is 0%, so the description was required to compensate, but it never touches the three parameters: what query should contain, how limit caps results, or the meaning of carrier values. The schema's own constraints (limit 1–10 with default 5; carrier enum of SKT/KT/LGU+/MVNO) are partly self-documenting, but the free-text query has no semantic guidance anywhere in the definition.

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 pairs a specific verb (검색합니다/searches) with a precisely scoped resource: 24-month TCO mobile phone conditions that are official/carrier-verified, have remaining validity, and contain no estimates or omissions. This filter criteria set clearly separates it from the sibling search_verified_products, which targets products rather than TCO conditions. There is no tautology or ambiguity.

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 '만' (only) framing signals that this tool is deliberately narrower than a general search, implying it should be chosen when verified, complete, in-effect 24-month TCO deals are required. However, it never names a sibling or states when to prefer search_verified_products over this tool, so routing is left to inference rather than explicit guidance.

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