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

With no annotations provided, the description carries the full burden. It discloses that the series is forward-only and cannot be backfilled, that early data may be sparse ('says so'), and that both legs come from the same source for internal consistency. It explains the sign convention (positive=premium, negative=discount) and mentions the `range` block in the response. This is solid disclosure, though it omits exact response structure/format.

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 compact yet information-dense. It front-loads the core question, then covers data source, cadence, interpretation, limitations, and parameter behavior in a logical order. No sentence is wasted, though it could be slightly trimmed without losing value.

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 single-parameter tool with no output schema, the description provides everything an agent needs to call it correctly: definition, timezone, frequency, source consistency, sign semantics, forward-only constraint, tier caps, and the response's `range` block. Nothing critical is missing.

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?

The schema already documents `days` with 100% coverage, including auto-clamping and tier boundaries. The description adds concrete tier limits (Free=30, Pro=365, Power=3650) and clarifies the 'capped by tier' behavior, plus the forward-only note about n_days being small early on. This goes beyond the schema and meaningfully helps the agent set expectations.

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 opens with a precise question ('Is Korean spot trading BTC at a premium?') and defines the exact metric: Upbit BTC/KRW (USD-converted) versus global BTC/USD in percent. It names the resource (Kimchi premium), the source (CoinGecko), and the data cadence (daily snapshots), making it unmistakable and clearly distinct from any sibling get_* tool.

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 states when to use it (when you need Korean BTC premium) and gives operational constraints: forward-only data since 2026-08, cannot be backfilled, and the `days` window is capped by tier with explicit tier limits (Free=30/Pro=365/Power=3650). It doesn't name an alternative tool to switch to, but given the unique metric, the guidance is essentially complete.

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