raw_cursor_left

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

There are no annotations provided, so the description carries full responsibility for behavioral disclosure. It does warn that the action 'May open a dialog or change project state' and advises inspecting the command name. However, it does not specify what side effects might occur, under what conditions, or the nature of the cursor movement (e.g., does it wrap at boundaries?). The warning is generic and does not fully inform the agent of the tool's behavioral traits beyond the basic movement. A score of 3 reflects partial disclosure with room for more specificity.

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 concise, with two sentences. The primary action is front-loaded: 'Move the cursor left by one unit.' The following sentence adds essential contextual warnings without excessive length. It avoids redundancy and every phrase serves a purpose. It is appropriately sized for a simple, parameterless action. A score of 4 reflects strong conciseness, though it could be slightly more informative without losing brevity.

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?

The tool has no parameters, no output schema, and no annotations, so completeness depends solely on the description. The description covers the basic function and alerts the agent to potential side effects, but it leaves ambiguity about 'one unit' (e.g., pixel, sample, grid unit) and does not explain the exact behavioral outcome. Given the large set of sibling cursor tools, agents might benefit from more context on how this differs from short/long jumps. The description is sufficient for a simple action but not fully comprehensive. A score of 3 reflects adequate coverage with notable 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?

The tool has zero parameters, and schema description coverage is 100% (vacuously). Since there are no parameters, the description does not need to explain parameter semantics. Baseline for 0 params is 4, and the description adds no conflicting information. It correctly states 'no-argument,' reinforcing the schema. Thus, a score of 4 is appropriate.

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 action: 'Move the cursor left by one unit.' It identifies the resource (cursor) and the verb (move), and adds the quantifier 'one unit.' While the name 'raw_cursor_left' already implies movement, the description specifies the exact scope. It does not explicitly differentiate from siblings like raw_cursor_short_jump_left or raw_cursor_long_jump_left, but the 'one unit' phrasing provides some distinction. A score of 4 is appropriate for clear purpose without explicit sibling differentiation.

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 provides no guidance on when to use this tool versus alternatives. It does not mention context, prerequisites, or conditions that would make this tool preferable to raw_cursor_right, raw_cursor_short_jump_left, or other cursor movement tools. The cautionary note 'inspect the command name first' is a general safety advisory, not usage guidance. There is no explicit 'when to use' or 'when not to use' information.

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