sqo_worktree_sandbox

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

With no annotations, the description carries the full disclosure burden. It usefully reveals the mechanism and location (Git worktree/snapshot under `.sqo/sandboxes/<name>`), but a mutation tool whose 'promote' writes files back to the real workspace and whose 'cleanup' removes sandboxes should say what promote overwrites, what cleanup destroys, and whether either is reversible — none of that is stated.

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?

It is a single front-loaded sentence with no filler paragraphs, but the version-stamped product branding at the front is pure noise and 'cleans up cleanly' is redundant with 'cleanup'. Neither phrase helps an agent decide or invoke.

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?

A five-action tool with a destructive promote/cleanup pair, no annotations, and no output schema needs more: what diff returns, whether promote requires confirmation or overwrites existing files, and what cleanup removes are all unaddressed. The description explains the concept but not the consequences an agent must understand before calling it.

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 coverage is 100%, so the enum actions and the workspace/name parameters are already documented, which sets the baseline at 3. The description reinforces the `name` parameter by showing it in the path `.sqo/sandboxes/<name>`, but it silently omits the 'list' action from its enumeration and adds no format or constraint detail beyond the 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 names the resource (isolated Git worktree/snapshot sandbox) and enumerates the operations — create, diff, promote, cleanup — which map to four of the five enum actions. It is specific enough to distinguish from unrelated siblings like sqo_edit_symbol, though the leading branding phrase 'Superpowers Isolated Experiment Sandbox (v10.0)' adds no discriminating information.

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?

Usage is only implied: 'zero-risk' and 'isolated experiment' suggest this is for risky or unverified changes, and 'promotes verified files' sketches a create→diff→promote workflow. There is no explicit statement of when to choose this over editing in place, no prerequisites, and no when-not guidance.

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