preview_cleanup

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 does this well by explicitly stating this is a dry-run simulation and that it returns 'items that would be removed' and reclaimable bytes, establishing a non-destructive preview. It stops short of an absolute statement like 'no files will be modified', but the dry-run terminology strongly implies it.

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 tightly structured with a one-sentence purpose, a clear Args section, and a Returns section. Every line earns its place, and the most important trait—dry-run/preview—is front-loaded.

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 four optional parameters and an output schema, the description covers the input semantics and the return shape sufficiently. It could be slightly more complete by explicitly directing the agent to clean_workspace for actual execution or restating that no changes are made, but the existing content is adequate for correct invocation.

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 description coverage is 0%, so the description must compensate for missing parameter documentation. It does: every parameter is listed with a meaningful one-line explanation, and 'older_than_days' gains important context as 'inactive for at least N days'. This adds real semantics beyond the raw schema fields.

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 opens with 'Dry-run simulation of workspace cleanup', which names a specific verb (simulate/preview) and a clear resource (workspace cleanup). It also differentiates itself from the sibling clean_workspace by framing this as a preview 'before executing', so an agent can immediately tell it apart from the actual cleanup tool.

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 clearly implies the tool is for planning: inspect items and reclaimable space 'before executing'. It does not explicitly name clean_workspace as the alternative to run when actual cleanup is intended, but the dry-run framing and 'before executing' language provide clear contextual guidance.

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