Get VNC coordinates to access a Grok Bot cloud agent's desktop; optionally wake the sandbox with confirmation and receive run_state and connect_url.
Account-level sandbox VNC coordinates. wake=true requires confirm=true. Returns run_state, connect_url, and websocket header names (not token values).
| Name | Required | Description | Default |
|---|---|---|---|
| wake | No | Wake the sandbox. Requires confirm=true. | |
| confirm | No | Required when wake=true |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The destructiveHint annotation already flags the safety profile, so the bar is lower. The description usefully adds the confirm requirement and names return fields, noting websocket headers are not token values, but it does not explain what is destroyed or what the destructive action actually does.
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 three short sentences with no filler, and it front-loads the resource domain before the wake/confirm rule and return details. Every sentence carries distinct information.
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?
With only two parameters and no output schema, the description partially compensates by naming return fields. However, it leaves the core purpose and when-to-use context underspecified for an agent choosing among many grokbot tools, so it is only minimally adequate.
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 100%, and both parameters are fully documented in the schema with the same wake/confirm dependency stated in the description. The description adds no syntax, format, or side-effect meaning beyond the schema, so this hits the baseline.
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 phrase 'Account-level sandbox VNC coordinates' names a resource domain but uses no clear action verb, leaving the actual operation ambiguous. It is distinguishable from account-management siblings, but an agent cannot confidently tell whether this retrieves, creates, or wakes a sandbox.
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 gives only the conditional prerequisite 'wake=true requires confirm=true' and no guidance on when to use this tool versus the many grokbot siblings. There is no context, exclusion, or alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.