env_gc

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains what gets removed, the age-based exclusion for environments without a TTL, and the dry-run safety path. It could mention whether removal is permanent, but the core destructive behavior and conditions are transparent.

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 compact and front-loaded: it states the action and criteria first, then the exception, then the dry-run behavior, then the recommended usage. Every sentence adds necessary information without 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?

For a one-parameter tool with an output schema, the description is largely complete. It covers what is removed, when to use it, and how to preview. It does not describe return values in detail, but the presence of an output schema reduces that burden.

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?

The schema already covers the single dry_run parameter at 100%, including its meaning. The description reinforces it with 'Pass dry_run to see what would go without removing it,' but adds little beyond the schema. Baseline 3 is appropriate.

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 the tool removes environments, specifying the exact criteria (TTL expiration or vanished VirtualBox VM). It is scoped and readable, though it does not explicitly contrast itself with the sibling env_rm, so differentiation could be stronger.

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 gives concrete guidance: call it before finishing a session to prevent short-lived environments from piling up. It also explains the dry_run option. It does not explicitly say when not to use it or when to prefer env_rm, but the context is clear enough for most cases.

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