pbs_prune

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

With no annotations provided, the description fully carries the burden. It clearly states it is a mutation that deletes recovery points, is synchronous, and has safety gates. It explicitly warns 'no undo' and 'PLAN is HIGH,' providing essential behavioral context for a destructive operation.

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 concise with several packed sentences covering purpose, safety gates, and behavior. It uses clear separation (e.g., 'TWO safety gates', 'Synchronous — returns prune decisions') without superfluous text, earning its place.

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 12 parameters (1 required) and an output schema (not shown), the description covers the most critical safety parameters but omits explanation of retention policy parameters like keep_daily. It adequately describes overall behavior and usage, though could be more complete on all parameters.

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 coverage is only 8%, so description must compensate. The description adds value for confirm and dry_run parameters (explaining their defaults and effects) but does not elaborate on retention policy parameters like keep_last or keep_daily, leaving most parameters unexplained beyond schema names.

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 starts with 'MUTATION: prune backup snapshots per a retention policy,' which clearly specifies the action (prune) and resource (backup snapshots) with a retention policy context. Among siblings, it distinguishes itself from pve_acl_prune or pbs_snapshot_delete by focusing on policy-based pruning.

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 explains the two safety gates (confirm and dry_run), their defaults, and the behavior of each (preview vs. actual deletion). It warns about the high plan and no undo. However, it does not compare to sibling tools or state when to use this vs. alternatives, leaving some implicit guidance.

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