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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds meaningful behavior beyond that: the inheritance/'live' propagation to assigned courses, the override semantics ('anything omitted stays the concept's own'), the auto mode meaning 'follow the learner', and a plan-tier requirement. It does not mention duplication or delete behavior, so not a full 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?

Dense but front-loaded: creation and inheritance come first, then token resolution rules, then mode/palette, then the plan gate. Every clause carries information, though the middle sentences pack several concepts tightly.

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 three-parameter tool with heavy nested objects and enums, the description supplies the mental model (concept-as-base plus overrides) that the schema alone cannot. An output schema exists so return values need no explanation, and the plan gate is disclosed. Minor gaps remain around naming conflicts and post-creation application to courses.

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 baseline would be 3, but the description adds genuine meaning the schema lacks: it explains that concept selects a base design and lists the concept names, clarifies that all other tokens override parts of the concept, and names the relationship between mode, palette, and darkPalette. This goes beyond restating field names.

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?

Specific verb (creates) plus resource (theme) plus a functional gloss of what a theme is: 'the look every course assigned to it inherits, live'. This distinguishes it cleanly from create_course, update_theme, and list_themes in the sibling set.

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 states a prerequisite ('Requires the Build plan or higher') which is useful gating context, but never says when to create a new theme versus update an existing one or reuse a concept, and names no alternatives. Usage is implied by the create verb rather than explained.

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