restore_checkpointLoad a checkpoint .xisf into the open view, or open as a new window if the view ID isn't active, to roll back to a saved processing state.
Roll back: load a checkpoint .xisf into the view in place (same id) or as a new window if the id is not open.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | ||
| path | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavioral detail beyond the destructiveHint annotation: it explains that the checkpoint is loaded into the existing view in place when the id is open, or into a new window otherwise. It does not explicitly warn about losing unsaved changes, but the in-place wording plus the annotation cover that risk.
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?
A single, front-loaded sentence conveys the action, resource, and the two key behavioral branches. Every word earns its place, with no redundant or vague 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?
The description is adequate for understanding the core behavior and the conditional window behavior, and annotations cover the destructive nature. However, with no output schema and no explicit parameter documentation, the agent still lacks full clarity on how to supply 'path' and 'id' correctly.
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%, and the description never explicitly defines the 'path' or 'id' parameters. It indirectly suggests path is a .xisf checkpoint file and id is a window identifier, but it leaves the required/optional relationship and parameter meanings mostly to inference.
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 a specific action ('roll back'), a specific resource ('checkpoint .xisf'), and the intended destination ('the view'). It also distinguishes in-place replacement from opening a new window, making the tool's purpose clear beyond its name.
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 'Roll back' prefix gives useful when-to-use context, but the description does not explicitly contrast this tool with siblings like undo, checkpoint, list_checkpoints, or open_image. The agent must infer when to choose restore_checkpoint over those alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.