uv.unwrap

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

Annotations declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the agent knows this is a mutating, non-idempotent operation. The description adds only 'Risk: standard; maturity: L3', which is generic maturity metadata, not behavioral disclosure. It does not explain what changes occur to the mesh or UV map, whether the operation is reversible, or what the output schema contains. With no annotation contradiction, but minimal added behavioral context, this is a 2.

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 description is short and front-loaded with the command name, but it spends its only substantive sentence on generic harness boilerplate rather than tool-specific information. It is concise but not informative — the brevity is under-specification, not efficient communication. A 3 reflects that it is not bloated, but the content does not earn its place.

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 Blender operation with 7 parameters, an output schema, and a large sibling family of UV and mesh tools, the description is severely incomplete. It does not state what the tool does, what the `method` and `margin` parameters control, what the output schema contains, or how this relates to the UV workflow (e.g., after marking seams, before packing). The generic risk/maturity line does not fill any of these gaps.

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 57%, and the description adds no parameter-level meaning beyond the schema. The schema already documents `selection` as a 'Selection receipt returned by mesh.select' and `_requestId` as a 'Stable request id for replay safety'. The description does not explain `margin`, `method`, or the enum values (indices, spatial, connected, normal), which are the UV-unwrap-specific parameters an agent would need help with. Baseline 3 applies because the schema covers the required parameters, but the description fails to compensate for the undocumented ones.

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 only states the command name `uv.unwrap` and generic harness boilerplate ('Risk: standard; maturity: L3'). It never says what the tool actually does — no verb, no resource, no effect. The title 'uv.unwrap' is a tautology of the name, and the description adds no functional meaning. An agent cannot tell this performs UV unwrapping on a mesh selection.

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 alternatives. The sibling list includes blender_uv_pack, blender_uv_mark_seams, blender_uv_inspect, and blender_uv_detect_overlap, but the description never distinguishes uv.unwrap from them. The only usage-related statement is generic policy boilerplate ('Per-request argument checks and session policy still apply'), which applies to every harness command and provides no tool-specific guidance.

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