create_diagram

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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that the tool handles layout, styling, and rendering automatically for graph types, that specs accept title/subtitle and focal elements, and that marking five focal elements erases the effect. It does not mention file overwrite behavior or permissions, but the creation semantics and return expectations are reasonably transparent.

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 front-loaded with the core purpose and then uses two clearly labeled bullets for input modes. It is compact, well-structured, and every sentence contributes either to mode selection or to the required discovery workflow.

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 7 parameters, no annotations, and an available output schema, the description is complete enough to guide correct invocation. It identifies required payloads per mode, points to the type-list and schema tools for dynamic discovery, and leaves return-value concerns to the output schema.

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 the baseline is 3; the description adds value by framing the conditional parameter groups (nodes+connections for graph types, diagram_type+spec for typed diagrams) and explaining what the agent must supply before calling. This mode-conditional interpretation is not as obvious from the schema alone.

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 opening sentence names a specific verb and resource: 'Create a new Excalidraw diagram of any supported type.' The two-mode breakdown (graph types vs typed diagrams) makes the scope precise and distinguishes it from sibling operations like modify_diagram, export_diagram, and mermaid_to_excalidraw.

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 gives explicit mode-selection guidance: pass nodes/connections for architecture/flowchart, or diagram_type+spec otherwise, and directs the agent to list_diagram_types and get_diagram_schema to fill in type-specific details. It does not explicitly contrast with siblings like modify_diagram or mermaid_to_excalidraw, but the usage context for this tool is clear.

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