image_prune

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

Annotations already indicate destructive=true, but the description adds essential behavioral context: default removes only dangling images, filters can expand to all unused images, valid filter keys are enumerated, and return information includes space reclaimed. This goes well beyond the annotation baseline.

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 well-structured: a one-sentence purpose, a focused paragraph on behavior and filters, and a concise args/returns breakdown. Each sentence contributes necessary information for a destructive prune operation without waste.

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?

Even though no output schema exists, the description states the return dict structure. It covers purpose, filter usage, default behavior, and references system_df. For a one-parameter tool with strong annotations, this is complete.

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?

The schema provides no descriptions for the `filters` object, but the description fully compensates by explaining valid filter keys (`dangling`, `until`, `label`) with value formats and the effect of omitting filters. This is high-value semantic information that is otherwise absent.

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 opens with a specific verb and resource: 'Remove unused local images to reclaim disk space.' It distinguishes from sibling prune tools by explicitly targeting 'local images' and explains the default dangling-only scope, which differentiates it from image_remove and other prune variants.

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?

Provides clear context: recommends 'Use system_df first to see how much space is reclaimable' and explains how to choose between dangling-only and all-unused images using filters. However, it does not explicitly name alternative tools or state when not to use it, so it lacks explicit exclusions.

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