ui_snapshot

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

Annotations already mark this as read-only and non-destructive. The description goes well beyond that by revealing behavioral details: it walks the whole SceneTree root including autoload HUD layers and popups, computes occluded_by via hit-testing, and offers a hash-based unchanged optimization. It also mentions the introspection state pixels can't tell (disabled, focused, checked, etc.), giving deep context about what to expect.

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 dense single paragraph with every clause contributing useful information; there is no filler or redundancy. It is longer than a simple tool would warrant, but this tool is genuinely complex. A bulleted structure would improve scannability, but the current paragraph is tightly packed and appropriately sized for the complexity.

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 thoroughly explains the return payload: per-control structure (path, class, text, rect, state flags, honesty flags), top-level information (focus owner, popups, viewport, hash), and the unchanged-UI shortcut. It also covers edge cases like occlusion and scoping, making it sufficiently complete for an agent to understand what it will receive.

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%, but the description adds meaningful usage semantics like 'path= to scope', 'interactive_only=true to slim', and 'since_hash' to detect unchanged UI. However, there is an inconsistency: the description says max_nodes defaults to 400, while the schema says default is 150. This slight factual mismatch prevents a perfect score.

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+resource: 'One-call UI snapshot of the RUNNING game' and enumerates exactly what is captured (visible Controls, state flags, occlusion). It explicitly differentiates from alternatives by stating it replaces the screenshot + find_ui_elements + get_control_rect + runtime_get_property round-trips for functional checks.

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?

Provides explicit when-to-use guidance: 'For functional UI checks this replaces... keep screenshot for VISUAL/render bugs.' It also explains scoping options (path=, interactive_only=true, max_nodes) and the since_hash mechanism for unchanged UI, establishing clear usage context and exclusions.

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