design_to_gcode_pipeline

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, but the description adds genuinely new behavior: slicing is conditional on a slicer being available, an inline 3D stage panel opens on success with automatic mesh decimation, an occupied plate causes a refusal at the slice step with suggested placements, and files are written into `output_dir`. These are side effects an agent cannot infer from the annotations, though the description never states what happens to pre-existing files in `output_dir`.

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 numbered pipeline steps are well front-loaded and the two prose blocks (INLINE 3D STAGE, MAKE DOORS) carry real information. But the docstring-style `:param:`/`:returns:` blocks duplicate the input schema verbatim and inflate length without adding value, and the MAKE DOORS paragraph is digressive about install state.

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?

With seven parameters, no output schema, and a real multi-stage workflow, the description is appropriately complete: it lists the return keys (SCAD, STL, G-code paths, weight, risks), explains conditional slicing, and documents the plate-occupancy rule. The remaining gap is that a mutation tool writing artifacts to disk says nothing about overwrite behavior or whether partial outputs survive a mid-pipeline failure.

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 100%, so the schema already documents all seven parameters. The `:param:` blocks largely restate those descriptions verbatim rather than adding new meaning; the only marginal value is the note that weight estimation uses `infill_percent` and that material affects temperatures, melt rate and cooling. Baseline 3 applies since the schema carries the semantic load.

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 names a concrete verb and resource chain — 'End-to-end pipeline: description → template → STL → analysis → GCode' — and enumerates the five stages, so an agent knows exactly what a single call produces. Sibling differentiation is present but muddled: it points at `compile_scad` as the iterate loop and `design_session` as the missing front door, without contrasting against closer siblings like `slice_model`, `generate_and_print`, or `smart_generate_from_template`.

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?

Usage is implied by 'One-call pipeline' and by the step list, and the MAKE DOORS block does name alternatives (`design_session`, `compile_scad`). However it never states a clean selection rule such as 'use this when you want STL + weight + G-code in one shot; use `slice_model` when you already have a mesh', and the note that `design_session` is not installed here leaves it ambiguous whether this tool itself is fully functional.

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