prune_old_snapshots

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

With no annotations, the description carries the behavioral transparency burden. It discloses that the operation deletes, that dry_run=true (default) only reports rather than deletes, and that deletion is governed by retention rules. It does not dwell on irreversibility or post-commit effects, but the safety default is clearly surfaced.

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 with no filler. It leads with the primary action, then states retention semantics, then gives the safety default. Every clause earns 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?

The description, combined with a fully documented schema, is enough for safe invocation: it explains the destructive behavior, retention rules, and the dry-run default. It is slightly thin on what a committed deletion returns or how the plan is presented, but response_format in the schema partially covers that.

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 100%, so the baseline is 3. The description restates parameter concepts in policy terms ('newest N per playlist', 'older than a cutoff', 'dry_run=true') but does not add meaning beyond what the schema already provides. It is helpful contextually, but not additive.

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 names a concrete action ('Delete old local snapshots') and specifies the exact retention policy: keep the newest N per playlist and optionally drop snapshots older than a cutoff. This clearly distinguishes pruning from one-off snapshot deletion and is not a tautology.

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 makes the use case clear: prune old local snapshots while optionally previewing with dry_run. However, it does not mention when NOT to use this tool versus related siblings like snapshot_retention_plan or delete_playlist_snapshot, so usage guidance is implied rather than explicit.

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