wait

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 30s cap and the default screenshot return. However it omits what happens on timeout (error, partial capture, or silent return) and whether waiting beyond 30s is clamped or rejected.

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?

A single sentence with the duration cap and default return front-loaded. Every clause carries information and nothing is wasted.

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?

Adequate for a simple zero-required-param tool, but with no output schema, no annotations, and 0% schema coverage, the description should have covered the 'seconds' cap semantics and the timeout outcome. It leaves the agent guessing about edge cases.

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 neither parameter is named, but the description maps to both: 'max 30s' constrains 'seconds' and 'by default return a screenshot' explains the 'screenshot_after' default of true. It conveys intent but no units, clamping behavior, or how to suppress the screenshot.

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?

States a specific verb (wait) and target (the UI) plus the two key behaviors: a 30s ceiling and screenshot-by-default. It is clearly distinguishable from the sibling 'screenshot', though the relationship between 'wait' and 'screenshot_after' is only implied.

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?

No guidance on when to wait versus calling 'screenshot' directly, and no mention of typical placement (e.g., after click/type_text to let the UI settle). The default-return note hints at an alternative but never names a condition for choosing it.

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