uv.pack

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

Annotations already declare readOnlyHint=false, implying a mutating operation, and the description does not contradict them. However, the text adds no behavioral context beyond annotations: it never says which scene state changes (UV layout of selected islands), whether it can cause unwanted overlaps, or what preconditions (e.g., a valid unwrap) are needed. The 'Risk: Maturity:' strings are boilerplate, not behavioral disclosure.

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 text is short, but inefficiency and emptiness is not conciseness in the spirit of the rubric. Both sentences are generic harness boilerplate ('PartMe...`uv.pack`', 'Requirements/argument checks and session policy still apply') that could attach to any harness command and add no tool-specific value.

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 mutating 6-parameter tool with nested objects, a validation schema, and a family of UV/selection-oriented siblings, the description is far too thin. It does not state what the operation accomplishes, how it relates to `uv_unwrap`/`uv_detect_overlap`, what preconditions hold (unwrapped mesh, topology version), or what the output describes. An agent selecting this tool must guess its behavior from its name.

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 67% – `margin` and any `_expectedSceneRevision` carry no schema description, and `selection` is only described as a receipt from `mesh.select`. The description contributes zero parameter meaning: it does not explain what `margin` is measured in, what unit is used, or that `selection` must reference a mesh with UVs. An agent cannot correctly set `margin` or reason about `selection` from the text.

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 is a tautology: 'PartMe Blender Harness command `uv.pack`' restates the tool name and adds nothing about what the tool does. The remaining content ('Risk: standard; maturity: L3') is generic metadata, so an agent can only guess from the tool name that it packs UVs. No verb and resource are stated.

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 no guidance on when to use this tool versus obvious siblings like `uv_unwrap`, `uv_mark_seams`, `uv_inspect`, or `uv_detect_overlap`. The only usage-adjacent text ('Requirements: Per-request/argument checks and session policy still apply') is generic harness boilerplate that applies to every tool, not a discriminator.

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