Clean up Docker

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

Adds real context beyond the annotations: it flags irreversibility ("Can't be undone"), mandates confirming with the person first while naming what will go, and warns that volume data is destroyed. Even though destructiveHint already flags the safety profile, the description supplies the operational confirmation requirement and the data-loss distinction.

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 dense sentences, front-loaded with the destructive scope and ending with the safety instruction. Every clause carries weight, though "Says how much space it freed" is slightly redundant given the tool has an output schema.

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?

For a bulk destructive tool with an output schema already covering return values, the description covers what is destroyed, the flag-dependent scope, irreversibility, and the confirmation expectation. Nothing needed to invoke it 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 100%, so the baseline is 3, but the description adds meaning by tying allImages to "all unused ones, not only the dangling ones" and stressing that with volumes the flagged data is gone, sharpening the consequence beyond the schema's neutral wording.

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?

States a specific verb ("Remove") plus the exact resource set (stopped containers, dangling images, unused networks/volumes, build cache). This clearly differentiates it from the individual remove_container/remove_volume/remove_network/remove_image siblings, which act on one target.

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?

Gives conditional rules that govern when content is actually removed ("allImages" for all unused images, "volumes" for volumes and their data). It does not explicitly name the per-item removal siblings as the alternative for targeted deletion, so the when-to-use-vs-alternative guidance is implicit rather than stated.

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