Prune snapshots

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

Annotations already include destructiveHint=true, so the description doesn't need to repeat that. It adds valuable context: defaults to dry_run, requires confirm for actual deletion, and that dry_run forces preview even without confirm. This goes beyond the schema and annotations, explaining the safety behavior. However, it doesn't specify exact effects on local snapshots or confirmation requirements in detail, but the core behavior is well disclosed. Since annotations cover the destructive nature, this is above average but not perfect.

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 sentence, front-loaded with the action and retention criteria, then adds critical safety notes. Every clause has a purpose: 'Local-only' sets scope, 'defaults to dry_run' and 'previews unless confirm=true' are essential for safe use. No 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?

For a destructive operation with 5 parameters, the description covers the action, scope, safety defaults, and confirmation requirement. The schema covers each parameter's meaning, so nothing essential is missing. The tool doesn't have an output schema, but for a prune operation the description doesn't need to explain return values; the core usage is fully understandable.

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 all five parameters are already described in the schema with clear meanings (e.g., 'older_than_days' explicitly says 'Delete snapshots older than N days'). The description adds the interplay between dry_run and confirm, which is not in the schema, but parameters themselves are already well-defined. Baseline 3 is correct because the schema does the heavy lifting.

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 states the verb 'delete' and the resource 'old snapshot files' with specific retention criteria (age, count, total size). It also clearly distinguishes from siblings like nuvio_inspect_snapshot and nuvio_restore_backup by focusing on deletion. The 'prune' name is expanded with concrete details.

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 explicitly notes 'Local-only; defaults to dry_run' and clarifies that 'dry_run=true always previews'. It implies when to use (for cleanup) but doesn't name alternatives like inspect or restore, though it's clear this is the deletion tool. No exclusions beyond the preview/confirm logic, so a 4 is appropriate.

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