openactors

Clean up old storage

clean-up-storage

Delete old datasets and stores that accumulate after every run, keeping only data newer than a chosen number of days. Use dry-run mode to preview and optional name matching to clear throwaway storages safely.

Instructions

Delete datasets and stores older than keepDays. Every run creates a dataset, so these accumulate; configuration stores are never removed. Use dryRun first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "clean-up-storage"
  }
}

Input Schema

Name	Required	Description
`match`	No	Regular expression on the storage name. When given, only matching storages are considered and the age check is waived — useful for clearing throwaway storages created the same day as real ones.
`dryRun`	No
`keepDays`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 5, 2026

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations, the description itself must convey risk. It does say this deletes data and that config stores are never removed, and it points to dryRun as a safe first step. However, it never states that non-dryRun deletion is permanent or irreversible, nor what dryRun actually produces, leaving a partial picture.

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

Conciseness5/5

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

Three sentences, no filler. The action is front-loaded, the rationale is one clause, and the safety instruction is last. Every sentence earns its place.

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?

For a destructive, 3-parameter tool with no output schema, this is adequate but not complete: it covers why to clean, what is protected, and a dry-run-first guideline. It leaves open what 'older than' is measured against, whether deletion is recoverable, and what result the tool returns, especially in dryRun mode.

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 covers only 1 of 3 parameters (match). The description adds meaning for keepDays ('older than') and introduces dryRun as a safety flag, but it does not explain dryRun's behavior when true/false; match's regex semantics are the schema's contribution. This is partial compensation for the 33% coverage gap.

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

Purpose5/5

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

The first sentence names a concrete operation ('Delete'), a specific resource scope ('datasets and stores'), and a condition ('older than keepDays'). The title and sibling list confirm this is the storage cleanup tool, so an agent can select it without confusing it with actor/task tools.

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

Usage Guidelines4/5

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

States 'Use dryRun first,' an explicit operating rule. It also gives the motivating scenario ('every run creates a dataset, so these accumulate') and a safety boundary ('configuration stores are never removed'). It doesn't spell out when-not-to-use, but no sibling tool competes for this job.

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