save_scene

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It only states the basic save action and default path, without mentioning whether the operation overwrites an existing file, what happens if no current hip file exists, or that saving to disk is a lasting, potentially destructive side effect.

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 compact lines front-load the main action and then clarify the one parameter. There is no filler, no repeated schema information, and no unnecessary detail.

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 one-parameter tool, the description covers the core invocation and default behavior, making it minimally viable. However, with no annotations and no output schema, edge-case behavior such as missing current hip file, overwrite semantics, and success/failure feedback remain undocumented.

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 gives only a nullable string parameter with no description, so the description's 'file_path: Destination path; defaults to the current hip file' is the sole source of parameter meaning. It fully explains the purpose and default of the single parameter, though it could add path format or extension constraints for a 5.

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 opening phrase 'Save the current Houdini scene to disk' uses a specific verb and identifies both the resource and the side effect, making the action unmistakable. It does not explicitly differentiate from related siblings such as export_file or write_cache, so it stops short of a 5.

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?

There is no guidance for when to choose save_scene over nearby alternatives such as export_file, write_cache, load_scene, or new_scene. The only contextual hint is the file_path defaulting to the current hip file, which explains default behavior rather than selection criteria.

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