Clear the figure

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

Annotations already declare destructiveHint=true, so the description isn't carrying the safety burden alone. It still adds real value by disclosing reversibility via ggb_undo, which the annotation does not express. It omits whether view/zoom state is also reset and gives no auth or rate-limit context.

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?

A single sentence with zero waste; the destructive scope is front-loaded and the recovery note is parenthetically appended rather than padding.

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 zero-parameter, no-output-schema tool with a destructive annotation, the description supplies everything needed to invoke it safely: what is removed, the scope, and how to reverse it. It could be slightly more complete by noting whether viewport settings survive the clear.

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 tool takes zero parameters, so the baseline is 4 per the rubric. The description correctly implies no filtering or scope arguments are accepted, and there is nothing further for it to document.

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?

States a specific verb (remove) and an unambiguous resource scope (every object) with the intent (start a new figure). The 'every object' scope implicitly distinguishes it from the object-level ggb_delete, but it never names that sibling, so differentiation is left to inference.

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?

Gives a clear condition for use ('to start a new figure') and names the recovery path (ggb_undo), which is genuinely actionable routing information. It stops short of an explicit when-not clause or naming ggb_delete as the narrower alternative.

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