viewport.capture

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

Annotations already provide readOnly, idempotent, and non-destructive hints. The description adds valuable behavioral context beyond those: viewport framing is temporary and user context is restored after capture. It does not detail the exact output or possible side effects on viewport_id, so it's not a full disclosure.

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?

One concise, front-loaded sentence with zero waste. It captures the core sequence of actions without redundant elaboration.

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?

The description covers the main purpose and context restauration but is silent on return semantics of the capture, the meaning of viewport_id and other parameters, and how 'semantic view' relates to the view enum. No output schema exists, so the description would need to explain capture output; it does not.

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 0%, so the description is expected to compensate with parameter meaning. It does not mention any parameter, though the schema names and enums are mostly self-descriptive.

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 multi-step action: temporarily frame an object, capture the 3D editor, then restore context. The verb and resource are clear and it distinguishes itself from viewport siblings like viewport.raycast by describing capture rather than raycast.

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 implies usage for non-disruptive viewport capture by highlighting the temporary framing and context restauration. However, it does not explicitly name alternatives or state when-not-to-use, leaving sibling differentiation to inference.

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