Remove an image

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

Annotations already flag destructive/idempotent, yet the description still adds real value: the durability consequence of deletion, the exact scope of force (also removes images used by a *stopped* container), and an approval requirement before acting. That is precisely the context annotations cannot convey.

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 compact sentences, each carrying distinct payload: what gets destroyed and how to behave beforehand. Nothing redundant, and the destructive outcome leads.

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?

A destructive mutation with an output schema present, so return values need no explanation. Annotations cover safety profile and the description covers consequences plus human confirmation — nothing an agent needs to invoke this correctly is missing.

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?

Schema coverage is 50% — only `image` is documented there. The description compensates by explaining `force` semantically (deletes even when a stopped container references the image) and by implying that the image is named/identified per its list output.

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?

Specific verb plus resource ("Remove a local image") that cleanly separates it from remove_container, remove_volume and remove_network. It stops short of addressing the one real ambiguity in the sibling set, prune, which can also delete 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?

It supplies the decision-relevant consequence ("has to be pulled or built again") and a hard prerequisite ("confirm with the person first, naming it"). It gives clear context but no explicit when-not or alternative routing to prune or remove_container.

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