Skip to main content
Glama

prune_old_snapshots

Delete old playlist snapshots, keeping the newest N per playlist and optionally removing those older than a set number of days. Use dry-run to preview before committing.

Instructions

Delete old local snapshots, keeping the newest N per playlist and optionally dropping those older than a cutoff; dry_run=true (default) only reports what would go Snapshot guide: take_playlist_snapshot (create), list_saved_snapshots (list), read_playlist_snapshot (read), diff_playlist_snapshots / snapshot_new_tracks / snapshot_removed_tracks (diff), restore_playlist_from_snapshot / restore_playlist_plan (restore).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runNoPreview only: perform the read side and return a deterministic PLAN without writing/deleting anything. Default true — pass false to commit.
playlistNoRestrict pruning to this playlist (ID or URI)
keep_lastNoSnapshots to KEEP per playlist (default 5)
older_than_daysNoAdditionally prune snapshots older than this many days
response_formatNo'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API objectconcise

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.26.1

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the burden of behavioral disclosure. It does explain the dry_run=true default preview behavior and the retention criteria, which is useful. However, it does not clarify what happens on commit, whether deletions are permanent, what the returned plan contains, or how the 'keep N' and 'older than cutoff' rules interact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is efficient and front-loads the core behavior. The dry-run clause is also valuable, but the trailing 'Snapshot guide' is tangential, and the sentence is grammatically truncated ('only reports what would go Snapshot guide').

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description, combined with 100% schema coverage, makes the tool minimally callable. However, there is no output schema, and the description does not explain what the returned plan looks like or what happens when dry_run=false, leaving a meaningful gap for a destructive maintenance tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 adds aggregate meaning by linking keep_last to 'newest N per playlist' and older_than_days to 'older than a cutoff', but it does not add per-parameter detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly names a specific verb ('Delete'), resource ('old local snapshots'), and a retention policy ('keeping the newest N per playlist'). It is obvious what the tool does, though it does not explicitly distinguish itself from the sibling delete_playlist_snapshot or snapshot_retention_plan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The Snapshot guide lists related create/list/read/diff/restore tools, which implies a snapshot-management context, but it never states when prune_old_snapshots should be chosen over alternatives. There is no explicit when-to-use or when-not-to-use guidance.

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

Deploy Server

Other Tools