save_checkpoint

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

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses that reusing a name overwrites the checkpoint, that CLO saves the checkpoint like Save As and changes the open file, and that the returned original_path points to the real file. These are non-obvious side effects an agent must know.

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?

Every sentence earns its place: purpose, timing, overwrite warning, Save As behavior, and final-save guidance. The information is front-loaded and tightly structured, with no 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?

For a tool with no output schema and no annotations, the description is remarkably complete. It covers what the tool does, when to use it, the overwrite behavior, the surprising open-file side effect, and the return field original_path, plus how to finish the save with save_project.

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 input schema only defines a single name parameter with a default, and the description does not directly document that parameter. However, 'Reusing a name overwrites it' adds meaningful semantics beyond the schema by warning about collisions, which is the main risk with this simple parameter.

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 action and resource: 'Save the whole scene so it can be restored later.' It also distinguishes itself from save_project by explaining that a checkpoint behaves like Save As and is not the final file save, so the agent can tell it apart from sibling tools.

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?

It explicitly tells when to use the tool: before risky edits such as sewing, deleting lines, or simulating, because the API has no undo. It also directs the agent to use save_project on the real file when finished, giving both a clear usage condition and an alternative.

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