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

Annotations already declare readOnlyHint=false and destructiveHint=true, so mutation risk is known; the description adds the genuinely non-obvious behavior that a badgeKey belongs to the TEMPLATE, so editing one layout propagates to all three pages using it. It also discloses the reset semantics of design:0. It doesn't explain whether an existing per-badge override is overwritten, which is the remaining destructive-behavior gap.

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 action and its scope lead the text, followed by key provenance and reset behavior; every sentence carries information. The heavy scare-quoting and conversational asides ('this is "this particular eyebrow should stand out"') cost it a little tightness.

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 3-param mutation tool with no output schema and thin annotations, the description covers scope, key provenance, propagation side effects, and reset behavior. Only the missing projectId semantics and the exact overwrite behavior on an existing badge keep it short of complete.

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 67% with the undocumented projectId, but the description adds real meaning for the other two: badgeKey is tied to the badge's own text slot and sourced from uichemy_get_page, and the key's template-level ownership is explained. Design values and the 0-reset are stated in both places, so the description goes beyond the schema on scope and persistence.

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?

Names a specific verb (set) and resource (badge design on one badge) and enumerates the concrete design values. It explicitly frames the scope as 'ONE badge' versus the site-wide badge look, so an agent can separate it from uichemy_set_badge_style without reading either schema.

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?

States when to use it ('this particular eyebrow should stand out'), when not (site-wide badge look is a separate thing), where the required key comes from (uichemy_get_page), and the reset condition (design: 0). The alternative is described by role rather than by tool name, but the branch is unambiguous.

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