pending_changes

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the bar is lower. The description still adds real context: the scope of what is tracked ('everything changed with live-preview tools since the last clear') and the fact that clear=true forgets the listed changes, which is a state effect the annotations do not surface.

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 sentences, front-loaded with the '[FOR CODE]' tag and the output contract before the usage instruction. Every clause (output contents, both code flavours, target locations, clear semantics) carries information; nothing is padded.

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?

There is no output schema, so the description carries that burden and does it well, enumerating the return payload (per-property diffs, paste-ready code, target pointers). Combined with a two-parameter schema and full annotation coverage, an agent has everything needed 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 description coverage is 100%, so both parameters are already documented. The description reinforces 'clear=true' as a follow-up action after writing code and mentions both code flavours, but adds no format or default detail beyond what the schema enumerates. Baseline 3 applies.

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 resource (the accumulated live-preview changes) and precisely what the output contains: before→after per property, ready-to-paste code in vanilla Three.js and/or R3F, and target locations. The bracketed '[FOR CODE]' tag signals intent well. It does not, however, differentiate itself against the sibling scene_diff, which an agent could reasonably confuse with this.

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?

Clear when-to-use ('Use it to persist a preview into source') and a lifecycle instruction ('call again with clear=true once the code is updated'). It stops short of naming alternatives, but the persist-then-clear workflow is stated explicitly rather than left to inference.

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