hydra_look

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

With readOnlyHint and destructiveHint annotations, the description goes beyond by explaining that it only reveals what render() shows (one output or a 4-up grid) and that hidden tabs cannot be captured. This adds valuable behavioral context beyond the annotations.

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 concise and well-structured, with the core purpose in the first line and essential usage guidance in subsequent sentences. Every sentence adds value, and the information is front-loaded for quick scanning.

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 description is complete for a simple single-parameter tool. It covers what the tool does, when to use it, limitations, and parameter specifics. The output (a screenshot) is self-evident, so no output schema is needed.

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 schema has no description for the max_width parameter, but the description explains it's a downscale target in pixels with a 64–1920 range. This compensates perfectly for the 0% schema coverage, giving the agent full understanding of the parameter's purpose and constraints.

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 precisely states the tool captures a screenshot of the primary tab's canvas, downscaled to a specified width. It clearly distinguishes this from other hydra tools (which are about rendering, state, or source management) by focusing on visual evidence capture.

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 explicitly instructs when to use it: 'look after writing and before describing anything,' and explains why it's necessary (a block can be black, blown out, or static). It doesn't name alternative tools, but the context of when to use it is clear. It also notes limitations with hidden tabs, which guides appropriate usage.

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