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 fails to state that capturing a screenshot is a safe, non-destructive read operation, whether it requires the app to be running, whether it waits for widget visibility, or what happens with the timeout_ms when no target is given. The timeout parameter's behavior is entirely unexplained.

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 concise, focused sentences that efficiently convey the core purpose and the primary behavioral distinction (with/without target). No wasted words. Could arguably add behavioral caveats but what's here is tight and front-loaded with the essential information.

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 screenshot tool with no annotations and no output schema, the description is adequately minimal but leaves gaps. The timeout_ms, save_path vs base64 behavior, and the type parameter's restriction to 'only for full-app screenshots' are all left to the schema. For a four-parameter tool with zero annotations, this is acceptable but not thorough—the interaction between type and target isn't clarified anywhere.

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 100%, so all four parameters have descriptions in the schema itself, establishing the baseline of 3. The tool description itself does not add semantic depth beyond what the schema provides—it doesn't clarify how type interacts with target, or what implicit wait means in context. The description adds little beyond the schema's own parameter 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 captures a screenshot with a specific verb+resource. Distinguishes two modes: full-app (no target) vs specific widget (with target). However, its interaction with get_widget_tree could be ambiguous, and it doesn't differentiate from the recording siblings despite being a clearly distinct operation.

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 explains the two usage modes (with/without target) which implies when each is appropriate. However, it doesn't explicitly state when each mode is preferred, doesn't discuss when to use this instead of start_recording, and says nothing about the save_path vs base64 return distinction—an important usage decision the agent must make.

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