Set UCS

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

Annotations only give readOnlyHint=false and destructiveHint=false; the description goes well beyond them by enumerating the exact pre-write refusal conditions (reserved name 'world', zero-length axis, non-perpendicular axes with the measured angle and 0.001° tolerance) and the axis normalisation behaviour. That is precisely the kind of mutation-safety context an agent needs.

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?

Front-loaded with the core action, then a dense but useful block on coordinate conventions and refusal rules; nearly every clause earns its place. Minor deduction for the trailing 'Pack: settings · lean: no.' fragment, which is internal jargon an external caller cannot interpret.

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 an output schema present, the description needn't explain returns, and it instead covers the non-obvious contract: WCS in/out for all tools, unit-vector normalisation, and the three refusal cases. Together with annotations and full schema coverage, an agent has everything required to call this correctly.

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 coverage is 100%, so the baseline is 3, but the description adds genuine semantic value: axes are normalised to unit vectors regardless of input length, the name 'world' is reserved and rejected, and perpendicularity is enforced with a stated tolerance. Only origin/coordinate-frame specifics are left entirely to the schema.

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?

States a specific verb and resource — 'Store a UCS table entry and make it current' — and grounds it against the real AutoCAD command, which makes clear this is a write/set operation, not the list or restore variants in the sibling set (ucs_list, ucs_restore).

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 explains the conceptual purpose of a UCS ('for the operator's own drafting') and the repository-wide WCS rule, which implies when this tool is appropriate. However it never explicitly states when to prefer this over ucs_restore or how it interacts with the current drawing state, leaving the when-to-use decision implicit.

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