prune_system

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

Without annotations, the description carries full burden. It discloses that volumes default to False, dry_run=True previews without changes, and that flags control what gets pruned. This covers key behaviors like safety preview and default scoping, though it could mention irreversible nature or auth requirements.

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?

Three sentences, front-loaded with purpose, no redundancy. Every sentence adds value: first sentence states purpose, second lists flags, third clarifies defaults and dry_run behavior.

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 tool with 8 params, no output schema, and no annotations, the description explains core functionality and defaults but omits explanation of env_id, agent_token, and return behavior. It is adequate but not fully complete.

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 0%, so description must add meaning. It explains the boolean flags (containers, images, volumes, etc.) and their defaults, adding context beyond the schema. However, env_id and agent_token are left unexplained, leaving gaps.

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 'Prune system resources for the given environment' clearly states the verb (prune) and resource (system resources in an environment). It distinguishes from sibling tools like prune_images, prune_networks, prune_volumes by being a bulk operation that selects multiple resource types via flags.

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 tells what to select via flags and mentions defaults, but does not explicitly state when to use this tool vs individual prune tools. It implies usage for bulk pruning, but lacks guidance on prerequisites, conditions, or exclusions.

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