screenshot_annotated

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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly discloses the core behavior—capturing a screenshot and drawing labeled markers—but does not explain the output format, whether an image file is produced, coordinate origin, or any permission requirements. The behavior is straightforward and not misleading, but details are missing.

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 two tight sentences with no filler. The primary action is front-loaded, and the use case is stated briefly and clearly.

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?

The tool is simple and its parameters are fully documented in the schema, but there is no output schema and the description does not specify what the tool returns—such as image path, base64 data, or an annotated image object. The phrase 'for AI reference' hints at the output purpose but does not define it, so an agent still has some uncertainty about invocation results.

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 explains the parameters. The description merely echoes 'points' and 'labels' without adding meaningful information about coordinate semantics, coordinate origin, or maxWidth behavior, so it stays at the baseline.

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 the tool takes a screenshot and annotates specific points with labels, which distinguishes it from the plain 'screenshot' sibling. It is specific about the action and resource, though it does not explicitly contrast with ai_screen_context or other alternative 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?

The description provides a use case: marking UI elements, buttons, or areas of interest for AI reference. This gives some context for when to use the tool, but it does not explicitly say when to prefer it over alternatives like screenshot, ai_screen_context, or ai_find_element, and it gives no exclusion criteria.

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