mouse_replay

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

With no annotations, the description carries the behavioral burden. It does disclose the replay action and the original-timing behavior, but it does not specify whether the path includes clicks/drags, whether the tool blocks until finished, or what happens when no recording exists.

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?

One short sentence with no filler; the core action, object, and timing behavior are front-loaded. Every word contributes.

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 one-parameter tool with no output schema, the description plus parameter schema are nearly sufficient to invoke correctly. The only notable gap is behavior when no recording has been made, which is a minor edge case given 'last recorded' signals the dependency.

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 schema already documents the only parameter at 100% coverage ('Replay speed multiplier (1.0=original, 2.0=2x faster)'). The description's 'with original timing' reinforces the default behavior but adds little beyond the schema.

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 states a specific action ('Replay'), a precise resource ('last recorded mouse path'), and a behavioral qualifier ('with original timing'). This clearly distinguishes it from mouse_record and direct pointer tools like mouse_move and mouse_click_xy.

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 phrase 'last recorded' implies a clear prerequisite: a prior mouse recording must exist before replaying. It does not explicitly name mouse_record as the required predecessor or state exclusions/alternatives, so it stops short of a 5.

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