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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description reinforces this with concrete, non-obvious behavior: calling it overrides the imported site's own buttons, and design: null restores 'the site's own look.' That is meaningful pre-call context about what gets overwritten and how to undo it, beyond what the annotations declare. It does not cover persistence, scope, or auth, so not a 5.

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 core purpose in the first clause, then the imported-project behavior, then the revert instruction — a logical order. Three sentences with modest stylistic padding ('hands the site's buttons over to our design system'), but nothing wasteful enough to penalize.

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 6-param mutation with destructiveHint and no output schema, the description covers the essential agent needs: what it changes, its effect on imported projects, and how to revert. Missing context about the required projectId and auth/persistence, but the annotations carry the safety profile, so the gap is minor.

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% and the schema already documents design (1-9/null), radius (px), and labelColor (site-wide ink). The description mainly restates those fields; its only added nuance, 'design: null to give them back,' paraphrases the schema's own 'null to clear the pick.' Marginal value over structured data, so a baseline 3.

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 concrete action ('Choose the button design...') and enumerates the exact adjustable facets — design, corner radius, size, icon, label colour — plus its location ('the Style Guide's Buttons panel'). It is clearly a styling tool, but it never distinguishes itself from the adjacent sibling uichemy_set_button_role, so it falls short of the 5 bar for sibling differentiation.

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 real context for when it matters: on an imported project it hands the site's buttons over to the design system, and 'until it is called, their buttons stay theirs.' It also explains how to revert (design: null). It stops short of naming an explicit alternative or when-not-to-use condition, so it is clear context without exclusions.

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