get_screenshot

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

The description adds significant behavioral context beyond the readOnlyHint annotation: it details behavior for missing/non-exportable nodes (base64 null), recovered off-canvas nodes (recovered: true), and empty nodes (empty: true). It discloses the auto-fit scaling logic and the reporting of exported dimensions and scale.

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 a single paragraph but is front-loaded with the output structure and uses clear technical details. It is concise given the amount of information covered, though breaking it into sections could improve readability. Every sentence adds value.

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?

Given the tool's complexity (exporting nodes with multiple formats, auto-fit, recovery logic) and the absence of an output schema, the description completely documents behaviors, edge cases (missing, recovered, empty), and output format. It is sufficiently informative for an agent to use correctly.

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 schema coverage is 100%, the description adds meaningful details beyond schema descriptions: it explains the auto-fit behavior when scale is omitted, notes that scale applies only to raster formats, and describes the 'recovered' and 'empty' flags in the output. It clarifies the purpose of the output fields, which the schema does not.

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 specifies the tool's action: 'Export nodes as images the model can see' with a detailed output structure and parameter effects. It distinguishes itself from sibling tools like 'export_pdf' and 'save_screenshots' by focusing on per-node image export with auto-fitting for model consumption.

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 how the tool works (auto-fit, format, scale) but does not explicitly state when to use this tool versus alternatives like export_pdf or save_screenshots. It provides usage context for the parameters (e.g., 'pass an explicit scale to force one') but lacks direct comparisons or when-not-to-use guidance.

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