imgui_transform_draw_layer

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states persistence ('persist until changed') and scope ('apply to all draw commands in the layer'), which is useful. However, it doesn't disclose whether the transform is cumulative with previous calls, how it interacts with per-command transforms or widgets, whether it requires the window/layer to exist first, or any performance implications.

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 tight two-sentence summary with meaningful persistence and scope information. No wasted words, though it could arguably front-load the 'persists until changed' behavior earlier for better scannability.

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 annotations and no output schema, the description should carry more weight. It covers purpose, persistence, and scope, which are the primary behaviors. However, for a transformation tool with 6 parameters, it lacks guidance on cumulative vs absolute semantics, interaction with existing transforms, or error conditions (e.g., non-existent layer/window). These gaps are notable given the absence of annotation support.

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 100%, so the schema already documents all 6 parameters well. The description adds that these transforms are layer-wide and persistent, which contextualizes the parameters slightly. However, it doesn't add format details beyond the schema, such as opacity clamping behavior or rotation direction (clockwise/counterclockwise) for the rotation parameter.

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 states the verb ('apply a transform') and the resource ('an entire draw layer'), listing the four specific transform types (translate, rotate, scale, opacity). It distinguishes from siblings which are mostly about input, rendering, and widget manipulation, though it doesn't name a specific alternative tool.

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 notes transforms 'persist until changed' and 'apply to all draw commands in the layer', implying it is a layer-wide operation versus imgui_update_draw_command which targets individual commands. However, it doesn't explicitly state when to use this vs per-command transforms, nor any ordering/exclusion guidance such as whether this must be called before adding draw commands.

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