cad_setup

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

Annotations declare destructiveHint=true and openWorldHint=true, so the write/network profile is already known; the description adds genuinely useful context beyond that: installation goes to this MCP's data directory, macOS requires an internal disk with file ownership, external/network volumes are refused before installation, and it explicitly does not start Blender, Fusion or a printer. Missing are rough duration/size or whether a partial install can be rolled back.

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?

Content is front-loaded with the core purpose, then the install behavior, then platform constraints and explicit non-effects. Each sentence contributes; the only mild redundancy is the restatement of the check-only mode already in the schema.

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 one-parameter tool with an output schema (so return shape needn't be described), this covers the install target location, platform restriction, refusal path, and non-effects on native signatures and other MCPs. What remains thin is failure behavior—what the agent should do if the runtime is absent or the volume check fails.

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?

With 100% schema description coverage and a single boolean whose default and meaning are already documented in the schema, the description adds no new syntax or format detail beyond restating that false only checks. Baseline 3 applies since the schema carries the parameter semantics.

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 opens with a specific verb and resource: check the optional confined build123d runtime, and it expands into what the install path does (pinned Python/packages in the MCP data directory, confined build plus STL/STEP round trip). This is clearly distinguishable from blender_mcp_setup and fusion_mcp_setup by resource, though those siblings are never named.

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 some usage guidance: 'With install: true' tells the agent the install path, and 'false only checks it' clarifies the default branch. However, it never states when an agent should call cad_setup versus cad_status or the other *_setup tools, and no explicit prerequisites (e.g., disk space, network access) are given before attempting the install branch.

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