prune_networks

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

Adds beyond annotations: lists filter keys, built-in exemption, and eligibility condition. Annotations already indicate destructive and idempotent; description confirms. Could mention idempotency explicitly.

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 concise sentences: purpose, rules, filters. Front-loaded with main action. 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?

Covers purpose, eligibility, filters, return value. Lacks explanation of idempotency (hinted by annotation) and impact on running containers, but sufficient for a pruning 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?

Schema has 0% coverage, but description compensates well: explains valid filter keys (until with RFC3339/duration, label with key=value). Adds meaning beyond 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?

Clearly states action: 'Remove networks that have no active container endpoints.' Differentiates from siblings like remove_network by specifying eligibility criteria and built-in network exemption.

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?

States when to use (prune unused custom networks) and built-in networks exempted. Lacks explicit alternatives or when-not-to-use compared to remove_network, but context is clear.

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