Prune Datastore

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds the dry-run capability, noting that it can show what would be pruned without removing, and discloses the return as a Task UPID or dry-run results. This goes beyond the structured annotations to describe safe preview behavior and asynchronous execution.

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 summary sentence is immediately followed by a compact Args list and a Returns line. Every parameter is listed with a one-line description, and the front-loaded purpose statement makes the tool's function instantly clear.

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 tool's complexity (11 parameters, retention policies) and lack of output schema, the description adequately covers the operation's purpose, dry-run mode, and return value. It does not delve into policy interaction details or potential long-running behavior, but the return 'Task UPID' hints at async execution. A minor gap is not explaining prerequisites or error conditions, but it is sufficient for agent invocation.

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 parameters are already well-documented. The description repeats the parameter list with minor clarifications (e.g., backup_type values, dry_run default), but does not add meaning beyond the schema. Baseline 3 is appropriate.

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 opens with a specific verb-action: 'Run a prune operation on a backup group to remove old snapshots per retention policy.' This clearly distinguishes it from sibling operations like garbage collection or verification. The resource is precisely the backup group defined by store, backup_type, and backup_id.

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 for retention-based snapshot cleanup but does not explicitly state when to use this tool versus siblings such as pbs_run_garbage_collection or pbs_protect_snapshot. There are no exclusions or alternative tool references, leaving the decision to the agent's inference.

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