start_product

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

The annotations state readOnlyHint=true and idempotentHint=true, but the description describes a workflow that runs multiple steps and may produce artifacts. It does add context that it will call ui_design_system and start_ui, and update project context, which goes beyond annotations. It also clarifies that it won't reference non-existent tools. This adds useful behavioral context without contradicting annotations (since readOnlyHint=true might be questionable but not contradicted).

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 (two sentences) and front-loaded with the main purpose. It covers key workflow actions and mentions tool dependencies in the first sentence. It's not overly verbose, but could possibly be more concise by removing redundant mentions. Still efficient.

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 complexity of a workflow-orchestrating tool with 9 parameters (many optional) and no output schema, the description provides essential context about the workflow, what it generates, and which tools it integrates. It also clarifies implicit behavior. It lacks details about return values or step-by-step behavior, but given the schema covers parameters well, this is adequate.

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?

The schema description coverage is 100%, meaning all 9 parameters are documented in the schema itself. The tool description does not add significant additional parameter semantics beyond what the schema already provides, except maybe the overall workflow context. Therefore, baseline 3 is appropriate.

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 clearly explains the tool's purpose: it is an entry point for a complete product design workflow that generates a delegated plan, creates PRD and prototype documents, and calls other tools. It also explicitly clarifies that it doesn't reference non-existent tools, which helps distinguish it from potential alternative tools. However, it doesn't provide strong differentiation from sibling tools like start_feature or start_ui, but the workflow context is clear.

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 implies when to use this tool: when starting a product design workflow from scratch, it will orchestrate the process and produce documents. It also explicitly notes it doesn't use gen_prd/gen_prototype, preventing misuse. However, it doesn't clearly say when NOT to use it or mention alternatives like start_feature, so it's not fully explicit.

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