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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description explains the mechanism behind the destruction: tokens and customFonts are replaced wholesale, so omitting keys discards them. That is high-value operational context beyond the flags, plus the plan-level auth requirement.

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 tightly packed sentences with no filler. The update semantics come first, then the destructive replacement caveat, then the plan gate, in descending order of operational importance.

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?

An output schema exists, so return values need no explanation. The description covers patch behavior, the destructive replacement gotcha, and the plan prerequisite. Given annotations carry the safety profile, the only minor omission is any reference to sibling tools for navigation.

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 the schema already documents id, name, tokens, and customFonts, including their own replacement notes. The description's 'send the full object, not just the changed keys' reinforces the same behavior rather than adding new parameter meaning, so the baseline 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?

States a specific verb and resource with scope: 'Partially updates a theme by id.' An agent can identify the operation and its patch semantics unambiguously. It does not explicitly differentiate from other update_* siblings (update_screen, update_course), but the resource noun is decisive.

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 word 'partially' implies when to use patch-style updates, and the plan requirement ('Requires the Build plan or higher') is a real gating precondition. However, there is no explicit routing to alternatives such as create_theme, get_theme, or delete_theme, leaving selection partly to inference.

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