Screenshot

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

The annotations only declare readOnlyHint=true; the description carries the behavioral burden and does so thoroughly. It discloses backend differences, the handle overlay cap and reporting behavior, the refusal with capability 'handle_overlay' on live AutoCAD, and the Image content block return format. This is far beyond what annotations provide.

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 information-dense with no fluff. It front-loads the main purpose, then uses each paragraph to explain backend behavior, parameter purpose, and return format. Every sentence contributes to correct invocation or expectation-setting.

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?

There is no output schema, so the description correctly states that an Image content block with PNG data is returned. It fully documents the single optional parameter, its constraints, backend-specific behavior, and failure conditions. For a simple screenshot tool with one optional boolean, nothing essential is missing.

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?

Although the schema already documents overlay_handles with high coverage, the description adds meaningful semantic context: handles are drawn at entity centres, every modify tool consumes a handle, and labels are the bridge between visual entities and actionable hex strings. It also explains failure modes and crowding behavior, enriching the parameter's meaning well beyond the 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?

The description opens with a specific verb and resource: 'Capture a screenshot of the current drawing view.' It clearly states what the tool does and its scope, and it distinguishes itself from broader export or zoom tools by focusing on the current view. The backend distinction further clarifies behavior without ambiguity.

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 explains backend-specific behavior (COM live window vs ezdxf matplotlib render) and when overlay_handles is available or refused. It does not explicitly name alternatives like view_zoom_and_screenshot, but it gives enough contextual guidance about when this tool is appropriate and when the overlay option will fail.

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