Save G-code and record the slice

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

Annotations only show readOnlyHint=false and destructiveHint=false. The description adds substantial behavior: never overwrites existing files, applies -2/-3 suffixes on collision, writes into fallback directories based on environment and folder existence, creates the gcode folder if missing, and still saves the file when the outcome store fails, setting outcome_recorded to False. This far exceeds the annotation coverage.

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 long but every sentence carries distinct, necessary information: purpose, return value, default naming, collision handling, directory fallback, and failure behavior. It is front-loaded with the main purpose and then structured logically, with no filler or redundant restating of the title.

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 description is very complete for a tool with no output schema: it covers return path, file-save fallback logic, and failure reporting. However, it doesn't mention what happens when there is no last successful slice (e.g., error behavior) and doesn't fully specify the success response shape beyond 'Returns the saved path'. These are minor gaps against an otherwise thorough definition.

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 has one optional filename parameter with no description (0% coverage). The description compensates fully by explaining the default filename pattern (<object>_<timestamp>.gcode), the collision-suffix behavior, and that the filename is the saving name. This adds meaningful semantic detail beyond the schema's bare type/default.

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 tool saves the last successful slice's G-code and records the slice under a filename, with a specific purpose for later print-outcome tracking. This is a specific verb+resource ('save ... G-code and record the slice'), but it does not explicitly differentiate itself from sibling tools like get_gcode or slice, relying instead on unique context.

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 clear workflow context: use after a successful slice, then pass the returned path to klipper-mcp's start_print. It also explains naming, collision handling, and fallback directory behavior. It doesn't explicitly state when not to use it or name alternative tools, so exclusions are absent.

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