checkpoint_restore

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

With no annotations, the description carries the full burden. It does disclose the key side effect—'replaces the scene'—which signals that the current scene will be overwritten. However, it does not mention potential data loss, prerequisites (an existing checkpoint), or how failure is handled if the name is invalid. Some important behavioral detail is missing.

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 a single sentence with no filler. It front-loads the core action ('Reload a checkpoint') and attaches a clarifying outcome ('replaces the scene') in parentheses. Every word contributes to the agent's understanding, making this an exemplary concise definition.

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 tool is simple (one required parameter, no output schema, no annotations), but the description leaves gaps: it doesn't explain what 'name' refers to or how to discover valid checkpoint names. Given that the pointer to checkpoint_save is present and the destructive nature is hinted at, the picture is not wholly inadequate, but it's not complete enough to ensure correct invocation without further investigation.

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?

The schema provides zero description for the 'name' parameter, so the description must compensate. It implies that the name identifies a previously saved checkpoint but does not explicitly state that 'name' is the checkpoint identifier or where to obtain valid names (e.g., checkpoint_list). Some semantic value is added, but not enough to fully cover the missing schema context.

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 clearly states the verb ('Reload'), the resource ('a checkpoint saved with checkpoint_save'), and the on-scene effect ('replaces the scene'). It explicitly references the sibling checkpoint_save, and the contrast with scene_open/scene_clear is implicit but sufficient for an agent to understand its function.

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 names checkpoint_save as the companion tool, giving context on how checkpoints are produced. It clearly implies this tool is for restoring a previously captured state rather than opening scene files or clearing the scene. It does not explicitly list exclusions (e.g., checkpoint_list for browsing checkpoints), but the intended use is clear.

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