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

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing the critical quirk that the response is a drawstoday.com link and 'carries no result' — information an agent would otherwise get wrong. It also names the upstream data sources, which signals freshness and provenance.

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?

Three tight sentences, front-loaded with the purpose, then per-game argument format, then the return-value caveat. Minor redundancy with the schema's draw description is the only waste.

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 no output schema, the description correctly takes on the return-value burden (a link, not the numbers) and identifies data sources. It omits behavior for invalid/out-of-range draw identifiers or missing games, a small but real 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 50% and the description restates the draw-parameter format largely as the schema already documents it, adding only the Korean term 회차. With `game` self-explanatory via enum, this is the expected baseline rather than added value.

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 specific resource (winning numbers) plus scope (latest draw or one past draw), and enumerates the three supported games with their identifier conventions. An agent can distinguish this from pick_numbers (generate) or check_ticket (verify) without opening a schema.

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?

Clearly instructs how to select the two modes: supply a draw number/date for a past draw, or omit for the latest. It does not explicitly name when a sibling like check_ticket would be the better call, but the context for correct invocation is unambiguous.

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