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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false. The description goes beyond them by naming exactly what is destroyed ('generated changes'), what is restored ('checkpoint_config'), and the resulting state ('the saved draft is not activated'), which is useful non-obvious side-effect detail.

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?

Two short sentences, zero waste, and the destructive action is front-loaded ahead of the resulting state.

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 3-param destructive tool with no output schema, the description covers the mutation, its side effect and the end state. Minor gaps (concurrency/409 handling, idempotency) are covered by annotations and the schema instead.

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 100%, so build_id, builder_run_id and expected_started_at are fully documented in the schema, including the stale-identity 409 behavior. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 and resource ('Discard generated changes', 'completing the builder run') and the tool is clearly the negative counterpart to acceptRevisionGeneration. It stops short of naming the sibling, so the contrast must be inferred from 'Discard'.

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 contrast with acceptRevisionGeneration and the mention of a review being discarded, but there is no explicit when-to-use / when-not-to-use statement or alternative routing. The 409 precondition is only in the schema, not the description.

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