ghost_sandbox

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

With no annotations, the description carries the full burden, and it does disclose meaningful traits: commit is atomic with fsync+replace, test runs an explicit command in a shadow copy of the workspace, and branches live in RAM. However it omits persistence/cleanup semantics for overlays, permission or concurrency constraints, and failure modes, leaving significant behavioral gaps for a 9-parameter mutation tool.

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?

Dense but front-loaded: lifecycle verbs come first, then the USE WHEN / DO NOT USE routing clauses. Every clause carries information, though the parenthetical glosses get crowded and read more like a compact spec than prose.

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 9-parameter, multi-command tool with no annotations and no output schema, the description covers the lifecycle model and selection intent but does not map parameters to commands or explain return values. It is the minimum viable framing rather than a complete one.

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, and it only partially does: it implies mutate uses path+content, test takes an explicit command, and the branch commands take branch_id. It says nothing about scores, timeout_s, hypothesis, or from_branch, leaving most parameters undocumented in both schema and description.

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 specific resource (ghost overlay) and enumerates the lifecycle operations (begin, mutate, test, commit, discard) with brief glosses for several of them. It is clearly distinguishable from siblings like vfs_mutate or hypothesis_branch, though it never names an alternative to route against. A solid verb+resource statement.

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?

Explicit USE WHEN ('speculative edits, a rollback point, competing fixes, running the project's own tests against staged content') and DO NOT USE ('before knowing the blast radius') clauses give real selection guidance. Alternatives among the sibling tools are not named, and the DO-NOT clause is terse/cryptic, keeping it short of a 5.

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