Empty a scene

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

The description adds significant behavioral context beyond what annotations provide. Annotations already indicate destructiveHint=true, so the destructive nature is known. But the description clarifies exactly what is destroyed (every element) and what is preserved (id, canvas, theme, title). It also notes that this is idempotent (idempotentHint=true is already in annotations). The only missing detail is whether undo is possible or what the output schema returns, but the output schema exists to specify 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 with zero wasted words. The first sentence defines purpose and scope concisely. The second and third sentences provide usage guidelines and sibling differentiation in a clear, front-loaded manner. The 'USE THIS when' and 'DO NOT use it' structure is exceptionally clear.

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 simple tool with only one parameter, clear annotations, and an output schema, the description is complete. It covers purpose, scope, preservation details, usage context, and exclusions. There is no missing critical information for an AI agent to correctly select and invoke this tool.

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% for the single parameter, and the schema already documents that sceneId must match a specific pattern and length, and gives a helpful description. The description adds context by referring to 'as returned by render_diagram or create_scene', which helps in understanding how to obtain the correct ID. This surpasses the baseline of 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 removes every element from a scene while preserving its id, canvas, theme, and title. It specifies the verb 'Remove every element' and the resource 'scene', and distinguishes itself from siblings like update_element and remove_element by describing its unique behavior of clearing all elements.

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 explicitly tells when to use the tool ('when the user wants to restart the drawing but keep talking about the same diagram') and provides a concrete user utterance ('scrap that, let's do it differently'). It also explicitly tells when NOT to use it ('DO NOT use it for corrections') and names the appropriate alternatives (update_element and remove_element).

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