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

Annotations already mark this readOnly=false and destructive=true, so the safety profile is known; the description adds genuinely non-derived context – that the call restores the template default and that it behaves the same under either key scheme, and that removal resolves rather than creates override conflicts. The word 'Safe' sits slightly awkwardly against destructiveHint=true, but it is a claim about idempotence/conflict resolution, not a contradiction. Gaps remain on no-op behavior when no override exists and on reversibility.

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 short sentences with the action front-loaded and no filler. Slightly idiosyncratic phrasing ('whatever the template ships', 'fighting pair') costs a little precision but does not pad the text.

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 small two-parameter mutation with no output schema, the description covers the effect but omits the practical details an agent needs: parameter formats, behavior when no override is present, and what a successful response indicates. Adequate but with clear 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?

Both parameters are required and schema description coverage is 0%, so the description carries the full burden. It conveys only that a single icon is targeted ('one icon'), hinting at iconId, and vaguely gestures at key-scheme variants. It says nothing about projectId, its requiredness, or the expected format of iconId.

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 action on a specific resource: putting an icon back to the template default, i.e. clearing an override. That distinguishes it reasonably well from set_icon/set_icon_color, though it never names a sibling explicitly or uses the word 'override' (the noun in the tool name and in uichemy_list_icon_overrides).

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 second sentence implies the scenario (resolving a 'fighting pair' of overrides) but gives no explicit when-to-use rule, no prerequisite such as listing overrides first to obtain iconId, and no statement of what to use when the goal is to change rather than clear an icon.

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