Preview pruning a recovery checkpoint

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

Annotations declare readOnlyHint=true, and the description confirms no deletion occurs, adding details on the destructive proposal (manifest removal, fail-closed garbage collection) without contradicting the read-only nature. No annotation contradiction.

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 concise sentences that are front-loaded with the core action and include necessary details without wasted words.

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?

Given the single parameter and presence of an output schema, the description covers purpose, constraints, and behavioral outcomes thoroughly, referencing appropriate alternatives.

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 has a single required 'checkpointId' with 0% description coverage, but the description does not explicitly explain this parameter. While the purpose is inferable, the description should have clarified that checkpointId is the UUID of the checkpoint to preview prune.

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 tool previews pruning a committed recovery checkpoint by returning a destructive proposal without deleting, distinguishing it from siblings like tiled_preview_prepared_checkpoint_discard which handle prepared checkpoints.

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?

Explicitly states that prepared checkpoints are rejected and suggests using the dedicated safe-discard preview when eligibility is proven, providing clear guidance on when not to use this tool.

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