compose

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

With no annotations, the description fully carries the behavioral burden. It explicitly returns the execution plan and results, explains partial failure behavior ('per-step failures do not abort the plan'), and notes error handling ('success=false with errors on failure'). This is comprehensive for an orchestrator tool.

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 concise (five sentences) and front-loaded with the core purpose. Each sentence adds essential information: purpose, prerequisite, return format, examples, and best-practice tip. No wasted words.

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?

Given the tool's complexity (multi-step orchestrator), the description covers all essential aspects: what it does, prerequisites, return structure including error handling, and usage examples. Without an output schema, it sufficiently explains the return values. It is complete for selecting and invoking the tool 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?

Despite 100% schema description coverage, the description adds significant value: it expands on the 'intent' parameter with detailed examples and a guideline to be specific. For 'dryRun', it explains the purpose and practical use. The description enhances the schema's meaning.

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 opens with a clear verb-resource pair: 'Run the agent orchestrator on a natural-language design intent.' It explains the classicize-plan-execute cycle, distinct from sibling tools like create_spec or generate_code which are more granular. The examples further illustrate exactly what the tool does.

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 ('Figma bridge only for Figma-touching intents'), provides multiple concrete examples of valid intents, and advises specificity ('name components, atomic levels, and target output'). This gives the agent clear guidance on when and how to invoke the tool.

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