raw_cursor_short_jump_left

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

With no annotations present, the description carries the full burden and does disclose that the action 'may open a dialog or change project state' and is a 'static no-argument' operation. It stops short of explaining what dialog or state changes could occur, but it responsibly flags side effects for what looks like a cursor movement.

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 two sentences, front-loads the core action, and every clause adds information: exact behavior, no-argument nature, Audacity context, and side-effect warning. No filler or repetition beyond the command-name prefix, which itself is useful for matching the underlying action.

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 zero-parameter, no-output-schema action, this is nearly complete: it gives the behavior, confirms no arguments, and warns about potential side effects. It loses one point because 'inspect the command name first' is an unusual instruction and no alternative-selection guidance is included, leaving a small amount of orientation work to the agent.

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 the baseline for no-parameter tools is 4. The description reinforces this by calling it 'no-argument,' leaving no ambiguity about invocation.

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 opening clause 'Move the cursor 1 second left' states a specific verb and resource with a precise magnitude, and the command label CursorShortJumpLeft echoes the exact Audacity action. This cleanly distinguishes it from sibling tools such as raw_cursor_long_jump_left and raw_cursor_short_jump_right.

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 effect statement implies the natural use case—moving the playhead/cursor left by one second—but the description never names sibling alternatives or states when not to use it. There is no explicit 'use X instead' guidance, leaving the agent to infer selection from direction and jump size.

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