Preview pruning recovery checkpoints in a batch

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

The description describes a destructive, non-atomic pruning process with sequential removal and garbage collection, which contradicts the annotations that set readOnlyHint to true and destructiveHint to false. This inconsistency severely misleads the agent about the tool's nature.

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 front-loaded with the core action and uses efficient sentences. Each sentence adds necessary detail, though the technical density could be slightly streamlined without losing clarity. Overall, it is appropriately sized for the complexity.

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 simple input schema and the existence of an output schema, the description sufficiently covers input semantics, behavior, error scenarios (stop on first failure, caching), and side effects (garbage collection). The contradiction with annotations is a flaw but does not diminish the completeness of the behavioral description itself.

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?

With 0% schema description coverage, the description fully compensates by explaining that checkpointIds must be committed recovery manifests, in UUID format, 2 to 32 items, canonicalized to lowercase, ordered by ID, and that prepared checkpoints or duplicates are rejected. This adds comprehensive meaning beyond the bare schema.

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 that the tool pins, canonicalizes, and orders checkpoint manifests, and it details the pruning process. The name 'prune_batch' and the sibling 'tiled_preview_checkpoint_prune' imply batch functionality, and the description explicitly mentions batch behavior with a range of 2 to 32 manifests.

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 does not specify when to use this tool over its siblings. No alternatives, prerequisites, or exclusions are mentioned; it only describes the internal process without context for selection.

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