prune_images

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

With no annotations, the description explains the destructive nature and the dry_run vs. execution flow. However, it fails to fully describe the behavior: what happens after the confirmation token is used, and how the agent_token parameter relates to the token. The flow is incomplete.

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 concise, with two sentences. It front-loads the purpose and critical warning, then explains the two-step process. Minor improvement could be structured bullets or explicit parameter mapping.

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?

No output schema exists, yet the description does not explain return values or the full lifecycle (e.g., what happens after token is provided). The workflow is unclear, and env_id's role is omitted. For a destructive multi-step tool, more context is needed.

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 description coverage is 0%, so the description must explain parameters. It only partially covers dry_run and implies agent_token is the confirmation token, but env_id is entirely undocumented. The mapping from agent_token to 'confirmation token' is ambiguous.

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 'Prune unused Docker images', specifying both the action (prune) and the resource (unused Docker images). This distinguishes it from sibling tools like prune_system or prune_volumes.

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?

The description provides clear guidance on the two-step process: using dry_run first then confirmation token. It warns about destructiveness but does not explicitly compare to similar prune tools (e.g., prune_system) for when to choose this over alternatives.

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