network_prune

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

Beyond annotations (destructiveHint=true), the description adds that built-in networks are never removed and only networks with zero connected containers are eligible. It also implies idempotency by stating networks already removed are not affected. The return dict is documented.

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, covering purpose, constraints, filter options, and return value in a few sentences. It is front-loaded with the main action and structured logically with no wasted 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 simple input (1 parameter, no output schema) and annotations present, the description is complete. It explains behavior, filter usage, built-in exemptions, and return format, leaving no ambiguity for selecting and invoking the tool.

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 coverage for the `filters` parameter, the description adds critical details: valid filter keys (`until` with RFC3339 or duration, `label` with key/value) and the effect of omitting filters. This fully compensates for the bare schema.

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.' It specifies the exact action and distinguishes by noting built-in networks (bridge, host, none) are never removed, which differentiates from general network removal tools like network_remove.

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 filter usage with valid keys (`until`, `label`) and their formats. It advises omitting filters to remove all unused custom networks. It does not explicitly compare to other prune tools but provides clear context for typical use.

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