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

The annotations indicate non-readOnly, non-idempotent, and non-destructive, but the description clarifies that the action discards generated changes (destructive in nature) and completes the builder run, which is not obvious from annotations. It also notes that the saved draft is not activated, providing key behavioral details beyond the annotations.

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 a single, dense sentence that conveys the action and consequence without redundancy. It is front-loaded with the core purpose and adds one critical caveat about draft activation. No filler.

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 mutation tool with no output schema, the description covers the action and effect. The schema provides additional necessary context for parameter usage. Minor gap: it does not describe any conditions under which the decline might fail (other than 409 on stale identity) or side effects beyond checkpoint restoration, but overall adequate.

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 input schema already provides descriptions for build_id and builder_run_id, but the description adds no extra detail for them. However, the schema description for expected_started_at includes crucial guidance about stale review identities returning 409, which is essential for correct parameter usage. This exceeds baseline for schema coverage.

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 clearly states the action ('Discard generated changes'), the resource (checkpoint_config), and the outcome (revision not activated). It also mentions completing the builder run, which is distinct from related actions like acceptRevisionGeneration or cancelBuilderRun. The title and description align, making the tool's purpose unmistakable.

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 implies usage when a user wants to discard changes, but it does not explicitly differentiate from similar tools like cancelBuilderRun or acceptRevisionGeneration. The schema description on expected_started_at adds critical guidance about copying started_at from the status being reviewed, which aids correct usage, but lacks explicit alternatives or when-not scenarios.

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