cleanup_workspace

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

With no annotations, the description carries the full burden and does so well: it discloses the destructive action is gated behind confirm=true, defaults to a non-destructive dry run, and lists explicit exclusions that are never touched (sources, WORKSPACE.md, reports/, third-party/, VMs under UOS_HOME). This is exactly the behavioral context an agent needs before a mutating call.

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?

Front-loads the operation and target globs, then default behavior, exclusions, and usage trigger. Every sentence earns its place with no filler.

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?

Despite a 2-param schema with no annotations, the description covers the mutation gate, the safe default, the exclusion set, and the use case; an output schema exists so return-value detail is unnecessary. Nothing needed to invoke it safely is missing.

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 supply meaning. It fully explains confirm ('with confirm=true delete', 'dry run by default') but leaves the workspace parameter's expected form (path vs. name) implicit. Partial compensation warrants the baseline-ish 3.

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?

States a specific verb+resource ('find/delete regenerable junk in the workspace') and enumerates the exact targets (__pycache__, .pytest_cache, build/, dist/, *.pyc/*.pyo/*.tmp), which no sibling tool covers. An agent can distinguish it from VM- and analysis-oriented siblings at a glance.

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?

Gives a clear when-to-use trigger ('Use before archiving or sharing the workspace') and states the dry-run-default posture, which sets the operating context. It does not name an alternative tool, but no sibling performs cleanup, so explicit routing isn't needed.

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