obs_screenshot

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

No annotations are present, so the description carries the behavioral burden. It discloses that the capture is immediate ('RIGHT NOW'), returns an image, and helps detect black-frame/dead-source states, which is useful behavioral context. Minor gaps like error behavior on invalid sourceName are not covered, but they are not critical for this simple read-only operation.

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?

Two sentences, front-loaded with the core behavior and outcome, and every sentence adds value: one defines the capture action and the other explains its intended diagnostic use. No fluff or repetition.

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 low-complexity, two-parameter tool with no output schema, the description adequately covers purpose, return type, and key use case. It does not explicitly address how this differs from obs_save_screenshot, but its emphasis on returning the image to Claude makes the distinction reasonably 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?

Schema coverage is 100% and already explains width and sourceName. The description adds valuable parameter context by advising to use the current program scene to see what viewers see, which goes beyond the raw schema.

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?

Description clearly states it captures a scene/source's current visual state and returns it as an image, which is specific and action-oriented. It does not explicitly contrast with sibling obs_save_screenshot, so it lacks direct sibling differentiation.

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?

It explicitly frames usage around visual verification of framing, layout, and camera liveness ('This is how Claude visually verifies...'). It provides clear context but does not list exclusions or point to alternative tools like obs_save_screenshot.

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