extract_critical_frames

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

With no annotations, the description carries the full burden. It discloses key behaviors: output is base64 JPEG screenshots, selection is based on a temporal window, and results are associated with test step titles. This goes beyond a minimal statement, though it doesn't cover edge cases or error handling.

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, information-dense sentence that efficiently conveys the action, output format, temporal scope, and result association. No redundant words; every phrase adds distinct value.

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?

With no output schema, the description provides a basic idea of the return value (screenshots with step titles) but lacks explicit structural details such as whether it returns a list, ordering, or how 'resolved' is presented. Given moderate complexity, the description is adequate but leaves some ambiguity.

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% with clear descriptions for all four parameters (trace_path, limit, lookback_ms, lookforward_ms). The description reiterates the temporal-window concept but adds no extra semantics beyond what the schema already provides, so the baseline 3 is appropriate.

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's function: extracting key screencast screenshots (base64 JPEG) from a temporal window around failure or trace end, with associated test step titles. It explicitly distinguishes itself from the sibling get_screenshot_at_failure by emphasizing multiple screenshots within a window and the step-title resolution.

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 clear context for when to use the tool: to capture visual evidence from a window around a test failure or the end of the trace. It doesn't explicitly mention alternatives or when-not-to-use, but the temporal-window context implies its specific use case among siblings.

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