diana_screenshot

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

Annotations only declare readOnlyHint and openWorldHint, but the description adds real behavioural detail beyond them: the tool may first switch the active view to MESH or RESULT (a state change the annotations do not convey), 'fit' rescales the camera, and output dimensions are bounded to 200-4096 px. What is missing is what the caller receives (an image payload vs. a file path) and whether the viewport stays changed after the capture.

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 front-loaded purpose sentence followed by a compact per-argument list; every line adds information an agent would otherwise have to guess. The phrasing around the default view is the only line that creates ambiguity rather than removing it.

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 five-parameter, zero-required, no-output-schema capture tool, the description covers purpose, all parameters, size limits and an important side effect (view switching). The only residual gap—result format—is minor and typical of image-returning tools, so nothing critical for correct invocation is absent.

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 must carry the load and largely does: it explains the three view options, gives the viewpoint enum a purpose ('camera direction'), advises 'top' for 2D XY-plane models, and supplies the 200-4096 px bounds that the schema omits entirely. The one weak spot is the note '(geometry view by default),' which conflicts with the schema default of 'current' and an enum that has no 'geometry' member.

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 opening sentence gives a specific verb and resource ('Capture DianaIE's 3D window as a PNG image') plus the intent ('to check the model visually'), which is far clearer than a bare name restatement. It does not explicitly contrast with near-neighbours like diana_plot_result or diana_model_snapshot, so an agent must infer that this one grabs the live viewport rather than a plotted chart or stored snapshot.

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?

Usage is only implied by the framing 'to check the model visually,' and the parameter notes give practical selection advice ('2D models in the XY plane are best seen from "top"'). There is no statement of when to prefer this over diana_plot_result or diana_model_snapshot, and no prerequisites or exclusions are listed.

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