Create a new Scratch project

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly reveals the destructive side effect ('Replaces any project currently open') and provides detailed input format for backdrops, including the special syntax for solid colors. This is transparent and covers the main behavioral traits an agent needs to know before invoking the 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 two sentences with no fluff. It front-loads the core purpose, then the critical side effect, then the backdrop options. Every sentence serves a purpose: the first defines the action and scope, the second warns of replacement, and the third provides input constraints. Highly efficient and well-structured.

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 simplicity (2 parameters, 1 required, no output schema), the description covers everything needed to call it correctly. It explains the effect (fresh project, replaces current), the backdrop options and syntax, and the side effect. No critical information is missing, and the description is fully sufficient for an agent to invoke the tool correctly without ambiguity.

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 coverage is 100%, so both parameters are already described in the schema. The description adds value for the 'backdrop' parameter by listing valid built-in options and explaining the 'solid:#223344' format for custom flat colors, which goes beyond the schema's generic description. For 'name', it adds no extra meaning beyond the schema, but the added backdrop detail justifies a score above the baseline 3.

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 states the tool's function with a specific verb and resource: 'Starts a fresh project in memory and sets its backdrop.' It also explicitly notes the destructive nature ('Replaces any project currently open'), which distinguishes it from sibling tools like add_backdrop that only modify the backdrop without resetting the project. The description differentiates from siblings by its core action of creating a new project rather than incrementally modifying one.

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 usage context by stating it 'Starts a fresh project' and 'Replaces any project currently open', which signals it should be used when a clean slate is needed. However, it does not explicitly name alternative tools like add_backdrop for scenarios where only the backdrop should change, nor does it provide explicit 'when not to use' guidance. The context is clear but lacks explicit exclusions.

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