imgui_draw

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

No annotations are provided, so the description carries the full behavioral burden. It discloses one behavioral trait — that repeated calls preserve earlier geometry (append semantics) — and supports the mode param with 'replaces it'. However, it doesn't disclose failure behavior (e.g., what happens if window doesn't exist), performance implications of 1024 max commands, or any coordinate-system/origin assumptions the agent needs to place geometry correctly.

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?

Two concise sentences that efficiently convey the core action, repeated-call behavior, and supported primitive list. No wasted words. Slightly light on structural guidance (e.g., no mention of the mode/id defaults), but front-loaded and minimal.

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 complex tool (19 command types, multiple coordinate/color params, no output schema, no annotations), the description is thin. It lists supported shapes but doesn't clarify per-type parameter usage, coordinate system, or how mode interacts with the id layer. The schema carries much of the load, but an agent would need to infer a lot about constructing valid command objects.

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 every parameter (id, mode, window, commands) already has meaningful descriptions in the schema. The description adds the layer-preservation behavior tied to 'append vs replace' mode, which is light value-add beyond the schema. It doesn't explain how the command type enum maps to which point parameters (p1-p4) are needed per type, which is the main ambiguity an agent would face.

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 it appends draw commands to a named layer in a window, with specific verb (append/draw), resource (layer in window), and a useful list of supported primitives. It doesn't explicitly differentiate from sibling tools like imgui_update_draw_command or imgui_transform_draw_layer, but the verb+resource pairing is reasonably distinctive given the 'draw' focus.

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 implies usage (drawing custom geometry in a window) but offers no explicit when-to-use guidance or exclusions. It mentions 'Repeated calls preserve earlier geometry by default' and supports multiple primitives, but doesn't contrast with imgui_add_hit_region, imgui_update_draw_command, or note any prerequisites like a window needing to exist first.

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