save_project

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

The description discloses meaningful behavior beyond the bare annotations: it writes a view as XISF with embedded processing history, saves companion views, checkpoint references, and tool history as manifest.json under a specified directory, and explains why .xosm cannot be used. It does not mention overwrite behavior or whether existing project files are replaced, but the artifact and location details are substantial.

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 two dense sentences with no filler. The first sentence front-loads the tool's purpose and artifact list, and the second provides a critical limitation. Every clause adds 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?

For a tool with three parameters, zero schema descriptions, no output schema, and no supplemental annotations, the description does not fully explain required inputs or expected behavior. It describes what is saved and where, but omits parameter semantics and what happens on success or failure, making it insufficient for reliable invocation.

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%, so the description must compensate for the undocumented parameters. It hints that 'companion views (masks/stars)' may relate to also_views, but it does not explain the meaning of id or name, nor how they affect the save location or manifest content. This leaves an agent unable to confidently construct correct parameters.

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 uses a specific verb ('Save') with a clear resource ('the processing project') and enumerates the exact artifacts: XISF view, companion views, checkpoint references, and manifest.json. It is easily distinguished from sibling tools like save_image or checkpoint because it describes a project-level save operation.

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 clearly conveys that this tool persists the full processing project state, and explicitly notes that .xosm projects cannot be written by scripts. However, it does not explicitly state when to prefer this over save_image or checkpoint, or when not to use it, though the project-level scope provides strong implied guidance.

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