prune_images

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

Explains behavior beyond annotations: details on dangling images, filter semantics (valid keys like dangling, until, label), and idempotent nature. Does not mention any side effects or requirements but adds useful context.

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?

Two well-structured paragraphs: first explains main behavior and filter semantics, second describes parameter and return value. Every sentence adds value with no redundancy.

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?

Given one parameter and no output schema, the description covers all necessary context: purpose, filter usage, return format, and helpful tip (use df first). Adequate for agent understanding.

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?

Input schema has 0% description coverage, but the description compensates fully by explaining the filters parameter in detail: valid keys, types (bool as string, timestamp/duration, label), and example usage for non-dangling removal.

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 clearly states the tool removes unused local images to reclaim disk space, distinguishes between dangling and all unused images, and contrasts with sibling tools like remove_image and other prune_* tools.

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 explicit guidance on when to use without filters (dangling only) and how to use filters for broader cleanup. Suggests using 'df' first to assess reclaimable space. Lacks direct comparison with remove_image but context is clear.

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