image_prune

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

The description details destructive behavior (removing images) and explains filter behavior (dangling vs all, valid keys). Annotations already indicate destructiveHint=true and idempotentHint=true, and the description adds valuable nuance without contradiction.

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-organized: purpose first, then detailed behavior, parameter documentation, and return value. Each sentence adds value without redundancy, achieving conciseness.

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 fully covers the tool's behavior, filters, and return value. It also references a related tool (`system_df`). No gaps remain.

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?

Despite 0% schema description coverage, the description thoroughly explains the single `filters` parameter: valid keys (`dangling`, `until`, `label`), types, default behavior, and returns format. This adds significant meaning beyond the bare schema.

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. It distinguishes between dangling images and all unused images, and differentiates from other prune tools (e.g., buildx_prune, container_prune) by specifying 'local images'.

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?

Explicitly states when to use without filters (dangling images) and with filters (all unused images via `filters={"dangling": false}`). Also advises using `system_df` first and lists valid filter keys, providing clear guidance.

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