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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the bar is lower, yet the description adds real value by bounding the destruction: only the draft is discarded, the submitted consultation is untouched, and applied changes are not reverted. It does not disclose what happens if the review_id refers to an already-applied or expired change.

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 key constraint is front-loaded in a single English sentence and the Korean text adds the when-to-use and exclusion detail rather than merely repeating. There is some duplication between the English opener and the first Korean sentence, which costs a bit of density but aids bilingual readers.

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 destructive, single-parameter tool with no output schema and no confirmation semantics stated, the definition covers intent and blast radius but omits error behavior (e.g. rejecting a review_id that is already applied or unknown) and whether any confirmation is required for the discard itself. Adequate but with clear gaps.

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 single parameter review_id is documented only as a 32-hex string pattern. The description never says what the ID identifies or where to obtain it (presumably from prepare_consultation_change), leaving the agent to infer the source and required state of the identifier.

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 verb ('Discard') and a precisely scoped resource ('an unapplied change preview') and immediately clarifies what is NOT affected (the submitted consultation). An agent can distinguish this from apply_consultation_change and revoke/withdraw flows without opening any 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?

Gives an explicit trigger ('사용자가 제안한 변경을 그만두겠다고 할 때') and two explicit exclusions: it does not withdraw the submitted consultation and does not revert an applied change. It points to a separate withdraw-proposal-plus-confirmation path, but never names an actual sibling tool, so routing is left slightly to inference.

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