production.uv_generate

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description adds two genuinely useful behavioral facts: output lands on a NEW Candidate (so the source asset is not mutated in place), and 'UV-immutable locks refuse generation' discloses a precondition that can abort the call. It stops short of saying what apply/verify do to the scene or what happens to a prior candidate.

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?

Two compact sentences with the core action front-loaded and the lock constraint placed as a closing caveat; there is no filler. The compression costs some readability ('configured angle/material/sharp/edge signals' is a noun pile), but nothing is redundant.

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?

An output schema covers return values, but for a five-parameter, non-idempotent generation tool at 0% schema coverage, the description omits the per-phase semantics (what apply vs preview actually changes), the meaning of operation_id/relationship, and the shape of options. The gaps are in exactly the places the structured data does not cover.

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 0% across five parameters, so the description carries the full burden and largely fails: only 'mode' is indirectly explained via the analyze/propose/preview/apply/verify/revert list. 'options', 'operation', 'operation_id', and 'relationship' are never mentioned, and given 'options' is a free-form object, an agent has no way to guess its contents.

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 concrete verb set (seam proposal, unwrap, shelf pack) and a concrete target (a NEW Candidate), which separates it from analysis siblings like uv_analyze and uv_validate. The phrasing is dense and jargon-heavy ('configured angle/material/sharp/edge signals'), but an agent can still tell it produces UV geometry rather than a report.

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 'analyze/propose/preview/apply/verify/revert' sequence gives implied workflow staging that maps to the mode parameter's default of 'analyze'. However, it never names a sibling alternative (uv_pack, uv_analyze, udim_apply_plan) or states when to prefer this generator over packing an existing unwrap, so selection still requires inference.

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