imgui_get_input_state

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 names what data types can be queried, which is helpful, but doesn't describe return format, whether values reflect the current frame or the previous one, or any latency/timing semantics of input state. For an input-reading tool, frame timing is a critical behavioral detail that is entirely absent.

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?

Single concise sentence that front-loads the purpose and enumerates the queryable categories. Efficient with no wasted words. Could arguably be more useful, but this is appropriately tight.

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 simple read-only query tool with one well-documented parameter, the description is mostly adequate. However, the lack of output schema means the description doesn't mention what the returned data structure looks like for each query type, and no timing/frame semantics are disclosed. Given the tool's simplicity and full schema coverage, this is minimally viable but leaves meaningful gaps.

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% (only one param 'queries' which is described as 'List of input state queries to perform'), so baseline is 3. The description lists the available query enum values in prose ('mouse position, mouse buttons, keyboard keys', etc.), which slightly adds context about what categories of queries exist beyond the schema. However, it doesn't explain semantic differences between lookalike queries like mouse_down vs mouse_clicked or key_down vs key_pressed.

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?

Description clearly states the tool queries input state (mouse position, buttons, keys, item interaction states) with explicit verb 'Query'. It distinguishes reasonably from sibling tools like imgui_press_key and imgui_set_mouse_pos which mutate input state rather than read it, and from imgui_state which appears to be a separate, broader state reader.

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 this is for reading the current UI input state, which is clear enough. However, it doesn't explicitly state when to use this vs the related imgui_get_state tool, nor does it mention prerequisites (e.g., whether a frame must have been drawn first for state to be meaningful). No exclusions or alternative naming provided.

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