wb_live_scale

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

With no annotations provided, the description carries the full burden, and it does disclose several useful traits: the operation is atomic in history, defaults to a non-destructive preview, and can hard-fail on non-scaleable leaves unless allow_partial is set. It does not say what the preview returns, whether failures return partial results or errors, or what happens to the existing selection or transform state after apply.

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?

Three short sentences, front-loaded with the operation and its pivot behavior, followed by the two guard conditions. No filler, though a slightly tighter grouping of the two conditional behaviors would read more cleanly.

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 10-parameter live mutation tool with no annotations and no output schema, the description covers the main destructive/safety posture well but falls short on return shape and on the meaning of the transform parameters that an agent must supply. It is adequate to avoid obvious misuse but not sufficient for confident first-call invocation.

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 10 parameters, so the description must compensate. It explains apply, allow_partial, and the pivot concept (implicitly mapping pivot_x/pivot_y/pivot_z), but leaves the core x/y/z semantics ambiguous (multipliers? absolute dimensions? per-axis?) and says nothing about rpc_dir or timeout. Over half the parameters remain undefined.

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 states a specific verb and resource ('Scale current selection') and adds meaningful scope details: it operates on the live selection, pivots around the selection pivot or an explicit pivot, and is recorded as a single WB history action. This clearly separates it from the offline sibling wb_scale, though it never names that sibling explicitly.

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 gives actionable conditions for two parameters ('Refuses non-scaleable leaves unless allow_partial=true' and 'Preview unless apply=true'), which tells the agent how to invoke it safely. It never says when to prefer this over wb_scale or wb_live_rotate, and there is no guidance on prerequisites such as having an active selection or connecting to a live session.

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