project_save

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

With no annotations provided, the description must disclose behavior itself. It states the tool writes state to a file and defaults to the original path, but it does not mention overwrite behavior, file format, or potential side effects. This is a meaningful gap for a persistence operation that could overwrite existing project files.

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 sentences with no filler. The core action is front-loaded, and the parameter explanation is minimal and directly useful. Every word earns its place.

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 and has an output schema, so return values need not be explained. However, for a save operation, details like file format and overwrite semantics would materially affect correct invocation and error handling. The description is minimally viable but leaves these gaps.

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 only describes output_path as an optional string or null with no explanation. The description compensates by explaining that the path is optional and defaults to the original project path. It does not specify format or extension constraints, but for a single optional parameter this is adequate.

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-resource pair: 'Persist the current project state to a file.' This clearly distinguishes it from siblings like project_new, project_open, and export_xml, which either create/load projects or export in a different sense. The default-to-original-path detail further clarifies it is the 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 gives no guidance on when to use project_save versus alternatives such as export_xml or export_render. It does not state when saving is appropriate, whether a project must be open first, or when the default output path should be overridden. This leaves usage context to the agent's inference.

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