done

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

With no annotations, the description carries the full burden and it does disclose the visible side effect (UI elements hidden, screen returned to the user). It does not disclose whether the call ends the session, whether further tool calls are valid afterward, or whether repeat calls are harmless — all material for a terminating tool. Useful but incomplete behavioral disclosure.

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?

Two sentences, zero waste, front-loaded with the calling trigger before the effect and then the parameter note. Each sentence earns its place and nothing is repeated from the schema.

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, no-output-schema termination tool, the description covers the trigger, the user-visible effect and the parameter format. The only meaningful gap is what the call returns or whether the agent's run ends here, which is a modest omission rather than a blocking one.

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 coverage is 0% and the single 'summary' parameter has no schema description, so the description must compensate — and it does, defining both content ('what you did') and format ('one short line'). It doesn't say whether the summary is shown to the user or logged, but the essential input contract is conveyed.

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 name 'done' is opaque, but the description immediately supplies the concrete effect: it hides the agent cursor, screen border and control panel and restores the user's screen. That is a specific, observable action an agent can distinguish from the action-oriented siblings (act, screenshot, window, etc.). It is not a textbook verb+resource phrasing, which keeps it just short of a 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?

The trigger is stated explicitly: 'Call once the task is complete (or you are stopping)'. That covers both the normal completion path and the abort path, which is the main ambiguity for a terminal-style tool. No alternatives are named, but none of the siblings appear to be competing cleanup/termination tools, so there is little left to disambiguate.

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