mcp-podman-crunchtools

Overview Schema Source Related Servers Discussions Admin

Image Prune Tool

image_prune_tool

Remove unused Podman images to reclaim storage. By default deletes only dangling, untagged images; supports filters and --all to clear all images not used by containers.

Instructions

Remove unused images, like podman image prune.

With no arguments only dangling (untagged, unused) images are removed.

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": "image_prune_tool"
  }
}

Input Schema

Name	Required	Description
`all`	No	Remove every image not used by a container, not just dangling ones (--all)
`filters`	No	Limit what is pruned (--filter). Keys: "until" (images built before a timestamp or Go duration, e.g. {"until": ["168h"]}; compares the build date, not when the image was pulled or tagged), "label" / "label!" (e.g. {"label": ["stage=ci"]}), "dangling" (["true"] or ["false"])
`external`	No	Also remove images used only by external containers, e.g. build containers (--external)
`build_cache`	No	Also remove the persistent build cache from --mount=type=cache (--build-cache)

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.1.0Oct 2, 2026

addedInput schema / properties / all

Added value: +{
+  "default": false,
+  "description": "Remove every image not used by a container, not just dangling ones (--all)",
+  "type": "boolean"
+}

addedInput schema / properties / build_cache

Added value: +{
+  "default": false,
+  "description": "Also remove the persistent build cache from --mount=type=cache\n(--build-cache)",
+  "type": "boolean"
+}

addedInput schema / properties / external

Added value: +{
+  "default": false,
+  "description": "Also remove images used only by external containers, e.g. build\ncontainers (--external)",
+  "type": "boolean"
+}

addedInput schema / properties / filters

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Limit what is pruned (--filter). Keys: \"until\" (images built before\na timestamp or Go duration, e.g. {\"until\": [\"168h\"]}; compares the build\ndate, not when the image was pulled or tagged), \"label\" / \"label!\"\n(e.g. {\"label\": [\"stage=ci\"]}), \"dangling\" ([\"true\"] or [\"false\"])"
+}

First observedv0.2.2Aug 1, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full disclosure burden, and it does surface the single most important behavioral fact: the default scope is limited to dangling, untagged, unused images rather than all images. It does not state that pruning is irreversible or mention any permission/daemon requirements, leaving some destructive-operation context unstated.

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?

Two short sentences, zero waste, with the core action front-loaded and the default-scope caveat immediately following. Everything stated earns its place.

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

Completeness4/5

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

An output schema exists, so return values need no explanation, and the schema fully documents the parameters. The description covers purpose and default scope adequately; the only gap is the absence of explicit guidance on when to prefer this over `image_rm_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 description coverage is 100%, so the four parameters (`all`, `filters`, `external`, `build_cache`) are already fully documented in the schema, including filter keys and semantics. The description adds only the no-argument default, which the schema's `all` default already implies; baseline 3 is appropriate.

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?

States a specific verb+resource ('Remove unused images') and anchors the semantics with a concrete analogue ('like `podman image prune`'), so an agent knows this is a bulk cleanup operation rather than targeted deletion. It never names `image_rm_tool`, the sibling it is most easily confused with, so it stops short of full differentiation.

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 second sentence clarifies the default invocation scope ('with no arguments only dangling (untagged, unused) images are removed'), which is useful operational context. However, it gives no explicit when-to-use/when-not guidance relative to `image_rm_tool` or `container_prune_tool`; the routing is only implied through the podman analogy.

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