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

Annotations already indicate this is a write operation (readOnlyHint false), not idempotent, and not destructive. The description adds valuable behavioral context: themes apply 'live', the token override semantics (concept as base, others override), and the plan requirement. It does not contradict annotations. It doesn't describe failure modes or return value, but the output schema likely covers that.

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 description is three sentences, well-structured, and front-loaded with the core purpose. It packs a lot of information about the token system without being overly verbose. Each sentence earns its place, and the structure is logical: purpose, token model, requirement. Slight improvement could be made by trimming minor details, but overall it's concise.

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 complex tool with nested token objects and many options, the description provides a strong overview: it explains the concept system, mode handling, and plan requirement. It doesn't enumerate every token property, but those are in the schema. It mentions the live effect on courses. The output schema is present, so return values are covered. Missing a note on how to handle customFonts, but that's in the schema. Overall, it's sufficiently complete for an agent to invoke correctly.

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% at the top level, with descriptions for name, tokens, and customFonts. The tool description adds meaning by explaining tokens.concept (listing all seven options), tokens.mode (light, dark, auto), and how palette and darkPalette work as overrides. This goes beyond the schema's generic description and helps the agent understand the design model. It doesn't explain every token property, but the schema covers those.

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 clear verb and resource: 'Creates a theme'. It elaborates what a theme is ('the look every course assigned to it inherits, live'), making the tool's purpose unambiguous. It distinguishes from siblings implicitly by the verb 'creates', and no other sibling has a similar description.

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 does not explicitly mention when to use this tool versus update_theme, delete_theme, or other related tools. It does provide a prerequisite ('Requires the Scale plan or higher') and explains the token model, which gives context, but it lacks any guidance on when not to use it or which alternative to choose. No explicit comparison with siblings is provided.

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