raw_exit

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

With no annotations, the description carries the full burden of disclosing behavior. It does state that the tool may 'open a dialog or change project state,' which is useful warning about side effects. However, it's vague about what dialog or state changes occur, and it doesn't address unsaved changes or whether the exit is immediate vs. prompt-driven. The 'inspect the command name first' clause adds caution but not concrete behavioral detail.

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 short and front-loaded, with the core purpose in the first sentence. The second sentence adds a cautionary note, though the phrase 'inspect the command name first' is somewhat vague and doesn't clearly indicate what action the agent should take. Overall, it's concise and mostly well-structured.

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 no-argument exit command, the description covers the basic purpose, side-effect potential, and static nature. However, it omits details like whether unsaved work will be prompted for, or if there's any prerequisite (e.g., a project must be open). The odd 'inspect the command name first' instruction doesn't fill this gap. Since there's no output schema and no annotations, the description should be more explicit about the action's consequences.

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 schema is empty, which gives a baseline of 4. The description reinforces this with 'Static no-argument Audacity action,' explicitly confirming that no arguments are expected. This is a small but useful addition for an agent that might otherwise look for hidden inputs.

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 a specific verb and resource: 'Close all project windows and exit Audacity.' This makes the operation unambiguous. However, it doesn't explicitly differentiate itself from sibling tools like project_close or transport_stop, which could also involve closing or stopping, so it's not a perfect 5.

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?

There is no direct guidance on when to use this tool instead of alternatives. The phrase 'inspect the command name first' implies caution but doesn't provide condition-based routing or mention alternative commands. The description relies on the agent's inference that 'exit' is only needed when shutting down Audacity.

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