Lists recent sandbox file writes with author and timestamp so you can review changes before undoing an unintended write.
List recent sandbox file writes (who wrote what, and when). Use before undoing a write you did not intend to make.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many recent writes to return (default 20) |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. 'List' implies a read-only, non-destructive operation and the sandbox scope plus returned fields are stated, but it omits pagination/ordering behavior and whether results span all files or only recent sessions.
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?
Two tight sentences, zero waste, with the purpose front-loaded and the usage cue immediately following.
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 simple single-parameter list tool with a fully documented schema and no output schema, the description covers what it returns and when to reach for it. Only richer behavioral detail (ordering, scope boundaries) 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?
Only one parameter (limit) with 100% schema coverage and a documented default of 20, so the schema does the heavy lifting. The description adds nothing beyond the schema about the limit or ordering semantics.
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 ('List') and resource ('recent sandbox file writes') and clarifies the record fields with 'who wrote what, and when'. It implicitly separates itself from write_file/read_file by being a history view, though it never names sibling tools outright.
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?
'Use before undoing a write you did not intend to make' gives a concrete triggering situation that points the agent toward undo_write as the follow-up action. No explicit when-not conditions or named alternatives, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.