network_prune

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

The description adds key behavioral details beyond annotations: built-in networks are exempt, only zero-container networks are eligible, and valid filter keys are listed. The return format is also given. There is no contradiction with annotations which mark the tool as destructive and idempotent.

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 and well-structured. It uses a clear opening sentence, followed by bullet-point-like details and explicit parameter and return documentation. No unnecessary words.

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 the simplicity of the tool (one parameter, no output schema), the description covers the parameter thoroughly, explains eligibility criteria, and notes the return format. It omits nothing critical, though permissions or side effects could be mentioned. Still, it is complete for practical use.

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?

With 0% schema description coverage, the description fully compensates. It explains the 'filters' parameter: narrows removal, valid keys 'until' and 'label', and default behavior (remove all unused custom networks). This adds significant meaning beyond the schema's bare object type.

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 'Remove networks that have no active container endpoints' with specific verb and resource. It distinguishes from sibling prune tools like container_prune, volume_prune, and image_prune by focusing solely on networks.

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 explains that built-in networks are never removed and that only networks with zero connected containers are eligible. It also describes filter keys. However, it does not explicitly contrast with other prune tools or state when to use this tool versus alternatives, but the context is sufficient.

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