capture_pie_screenshot

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

Adds real behavioral context beyond the annotations: the write is destructive to output_path, and with include_ui=true a cropped HUD frame overwrites the file one frame later (ui_overwrite_next_frame), so the final file is not what a naive caller expects. It also discloses the synchronous ReadPixels path omits UMG/Slate HUD. It does not mention auth/permission needs or the 8s give-up limit (that lives in the schema).

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?

Front-loaded with the core action, then the conditional HUD caveat, then the return shape. Dense and technical but every clause carries information; the trailing 'Returns:' block partially repeats the first sentence's enumerated outputs but is justified since no output schema exists.

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?

With no output schema, the description supplies the return keys, the destructive write target, the HUD omission, and the delayed-overwrite hazard — everything an agent needs to call it correctly and reason about the resulting file. Both parameters are fully covered.

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%, so the schema already documents both parameters, including the 8s SDR-only timeout and auto-naming rule. The description's include_ui explanation largely restates the schema's own description of the same overwrite behavior, adding little beyond what is already structured.

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?

Names a precise verb and resource ('Write a PNG of the game viewport (else the active editor viewport)') plus the mechanism (synchronous ReadPixels) and the HUD exclusion. An agent can tell this is a PIE/editor screenshot capture, distinct from sibling capture_viewport or high_res_screenshot, though neither sibling is named explicitly.

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 include_ui paragraph describes a conditional path during PIE, which implies the usage context, and the parenthetical '(else the active editor viewport)' implies the non-PIE fallback. However, there is no explicit when-to-use/when-not guidance and no routing to the similar sibling capture tools, leaving the agent to infer.

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