thunder_look

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

With no annotations, the description must carry the behavioral burden. It does disclose that the tool returns a file path, which is useful, but it does not state whether the screenshot covers the viewport or the full page, what image format is used, or whether the operation waits for page load.

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 a single compact sentence that front-loads the action and then states the return value. Every phrase earns its place.

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 zero-parameter visual inspection tool with no output schema, the description gives enough to call it and know the return type. It could be more complete by specifying whether the capture is viewport-only or full-page, but the core call is unambiguous.

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?

The tool takes zero parameters, so there is no parameter semantics to explain. The baseline for zero-parameter tools applies, and the description correctly avoids inventing parameter details.

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 states a specific verb and resource: taking a screenshot of the current page. This clearly distinguishes 'look' from reading via thunder_read or thunder_human_read, but it doesn't explicitly name alternatives, so it falls short of full sibling differentiation.

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?

Usage is implied by the phrase 'current page,' but the description never says when to prefer thunder_look over thunder_read or thunder_human_read. No exclusions or alternative tool guidance are provided, leaving routing to inference.

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