Screenshot

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

The description goes far beyond the simple readOnlyHint annotation, detailing backend-specific behavior (COM vs ezdxf), the overlay_handles capping behavior, the refusal in live AutoCAD, and the return format (Image content block with PNG data). This is excellent behavioral disclosure for an agent.

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 well-structured with a clear opening sentence, followed by backend details and overlay behavior. While somewhat lengthy, every sentence adds necessary behavioral context, and the formatting makes it easy to scan. Slightly verbose but not wasteful.

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 all essential aspects for a screenshot tool: what it captures, backend differences, the overlay feature's purpose and limitations, and the return type. Without an output schema, this description sufficiently explains what the agent can expect, making it complete for its complexity.

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 already documents overlay_handles with 100% coverage, but the description adds substantial meaning: it explains the motivation (connecting circles to hex handles), the capping behavior, and the backend-specific limitation. This goes beyond the schema's basic label definition.

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 clearly states 'Capture a screenshot of the current drawing view' with a specific verb and resource. However, it does not explicitly distinguish itself from sibling tools like view_zoom_and_screenshot, relying on the phrase 'current drawing view' to imply no zooming.

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 strong context for when to use the overlay_handles parameter, explaining the need to map visual entities to handles. It also gives a clear exclusion: live AutoCAD refuses overlay_handles, so users know to expect that limitation. However, it doesn't explicitly compare with alternative screenshot/zoom tools.

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