set_viewport_shading

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

The annotation declares idempotentHint true, so the agent knows calling it multiple times has the same effect. The description adds the list of valid modes, which is helpful, but doesn't explain side effects (e.g., whether it changes render settings or affects other tools). It doesn't contradict the annotation, and since idempotency is already provided, the description adds some value with the mode list but not much else.

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 one short sentence with the action and the allowed values. It's front-loaded with the verb 'Set' and the resource, and the list of modes is directly relevant. No wasted words.

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 simple one-parameter tool with an output schema (which likely confirms the change), the description covers the essential valid values. It doesn't mention prerequisites like needing a 3D viewport, but given the clear naming and sibling context (e.g., get_viewport_info), it's nearly complete. The lack of usage guidance is a minor gap, but the tool is simple enough that the description is sufficient.

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 schema has one parameter 'mode' with no description or enum. The description enumerates the possible values (WIREFRAME, SOLID, MATERIAL, RENDERED), which directly adds meaning beyond the schema. Since schema coverage is 0%, the description is essential and this is a significant addition. However, it doesn't clarify the exact semantics of each mode (e.g., what RENDERED implies), so it's adequate but not fully detailed.

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 states the tool's purpose clearly: 'Set viewport shading mode' with a list of valid modes. It identifies the specific action (set) and resource (viewport shading), which is understandable on its own. It doesn't explicitly distinguish from siblings like get_viewport_info or capture_viewport, but the naming and description are clear enough that an agent would recognize this is for changing the shading mode.

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 provides no guidance on when to use this tool versus alternatives, such as set_viewport_camera or frame_all. It doesn't mention any context like needing an active viewport or whether it affects all viewports. An agent might need to infer when this is relevant, but it's not explicitly stated.

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