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

Annotations only cover the read/write safety profile, and the description goes well beyond them: it discloses public visibility ('Everyone sees it'), persistence ('it stays yours'), cost per call, input coercion behavior (colors 'changed to the nearest its part can take'), and a prerequisite gate for locked shapes. These are exactly the traits an agent needs before mutating shared state.

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?

Front-loaded with the action, then the argument contract, then the side effects and cost. Dense and largely waste-free, though the clause 'as a person does in a browser' is decorative and the run-on sentence could be split for scannability.

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 7-parameter, all-optional, nested mutation tool with no output schema, the description covers the important unknowns: partial-update behavior, color format and snapping, visibility, persistence, cost, and the locked-shape prerequisite. What remains unclear is whether omitted parts are preserved unchanged and why 'head' is listed separately from face-related siblings.

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 coverage is 0% and the only inline param descriptions are the '#rrggbb' color format, so the description must carry the load. It does explain that shape values are numbers referencing `appearance` and that eyes take a color only, but it does not explain what the 1-6 shape range means, nor the semantics of supplying color without shape or shape without color.

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 specific verb and resource ('Changes how your character looks') and enumerates exactly which body parts are addressable. It differentiates from unlock_shape ('A locked shape can't be chosen here: unlock_shape buys it') but never explicitly contrasts with the sibling `appearance` read tool, only referencing it obliquely as the source of shape numbers.

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?

Gives a clear operational rule — 'Give only what changes' — establishing partial-update semantics, plus an explicit exclusion and alternative for locked shapes. It also flags the cost ('Costs one edit'), which shapes when an agent should batch changes. It stops short of stating when to inspect via `appearance` first.

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