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

Annotations only say readOnlyHint=false, destructiveHint=false. Description adds significant behavioral detail: transactional all-or-nothing, layout runs once and never again, returns element uids keyed by node ids, and placement below existing content. This goes far beyond annotations.

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?

Dense but every sentence adds value: core purpose, layout behavior, transactional guarantee, limits, shape guidance, edit path, and licensing. No fluff, well front-loaded.

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 complex tool with nested objects and no output schema, description covers input format, constraints, layout behavior, return value, and alternative. Nothing missing that an agent needs to call 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?

Schema coverage is 57%, so description must compensate. It clarifies nodes/edges semantics (no coordinates, local ids), shape meanings (diamond=decision, etc.), and groups behavior. It doesn't cover origin_x/origin_y in detail but implies defaults. Adequately compensates for gaps.

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 (draw), resource (whiteboard diagram), and input format (semantic graph). Differentiates from create_whiteboard and create_whiteboard_elements by emphasizing server-side layout and no coordinates. The distinction is explicit.

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?

Explicitly says when to use (semantic graph input) and when not (edit via update_whiteboard_elements, split >20 nodes). Also mentions Pro workspace requirement, which is a usage condition. No ambiguity.

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