screenshot

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

Despite no annotations, the description discloses that it is a read-only snapshot operation, notes it fails if the instance is down, and implies it is non-destructive. However, it does not explicitly state it does not modify state or require special permissions, but the nature of a screenshot makes that clear.

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?

Four concise sentences with key information front-loaded: purpose, alternatives, and failure condition. No redundant or extraneous content.

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 simple screenshot tool with one parameter and no output schema, the description covers purpose, usage guidance, failure condition, and return format (PNG). It is fully sufficient to enable correct use.

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?

Only one parameter (instance) with 0% schema coverage. The description mentions 'an instance's window' hinting that the parameter identifies the instance, but does not explain its default value or range. Barely compensates for the lack of schema documentation.

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?

Clearly states it takes a full-display PNG screenshot of an instance's window. Explicitly distinguishes itself as the only way to see the screen and contrasts with parse_screen and observe='screenshot' on action tools.

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?

Provides explicit guidance: 'always look before you act', recommends using parse_screen for element list with coordinates, and suggests prefering observe='screenshot' on action tools to act and see result in one call. Clearly outlines when to use this tool versus alternatives.

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