env_screenshot

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the operation is side-effect-free ('reading a screen changes nothing'), declares the tool needs nothing from the guest ('not even a network'), and reveals the lag behavior that could otherwise confuse an agent interpreting results.

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?

Every sentence earns its place: the first states the primary action, the second gives the key use case, the third clarifies scope and safety, the fourth distinguishes from environment-only input tools, and the last covers the running precondition and lag caveat. The description is front-loaded and free of filler.

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 single-parameter tool with an output schema, the description is complete. It covers purpose, accepted target types, preconditions, safety, and a known timing quirk. There is no missing information an agent would need to decide whether to call this tool and how to interpret its behavior.

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 description coverage is 100%, so the schema already documents the `name` parameter as 'name of the environment, golden image, or VirtualBox VM.' The description adds a little clarity by restating accepted target kinds and emphasizing the tool works on any VirtualBox VM by name, but it does not meaningfully expand parameter semantics beyond what the schema provides.

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 opens with a specific verb-resource pair: 'Capture a running machine's screen and return it as an image.' It also distinguishes this tool from the input-oriented sibling tools by clarifying that env_type, env_keys, env_click, and env_scroll operate only on environments, while env_screenshot can also target golden images and unmanaged VirtualBox VMs.

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 explicitly states when to use the tool: 'This is how to see a guest that has no SSH.' It provides clear preconditions ('The machine must be running'), notes a timing caveat ('The screen lags behind keystrokes'), and gives follow-up guidance to take a fresh screenshot after typing or key presses. It also signals a safe expansion of scope by noting the tool works for machines terrarium does not manage.

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