One-Call UI Review

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

With no annotations, the description carries the full burden. It discloses the Playwright dependency and that it returns prioritized issues and mismatch regions, but does not state side effects such as writing screenshots/heatmaps to disk or how overwrite affects prior output. This is partial but not complete behavioral context for a 10-param tool.

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 dense sentence that front-loads the core action and return value, with the Playwright requirement appended last. No wasted framing, though the requirement could be separated for scannability.

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 complex 10-parameter tool with no output schema and no annotations, the description gives a reasonable conceptual picture of the return (prioritized issues, mismatch regions) and the key prerequisite. However it omits side-effect/file-output details and the relationship to the granular sibling tools, leaving gaps an agent must infer.

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 high (~80%), so the schema already documents most parameters including ranges and defaults. The description adds only the mapping of 'optional FigCraft reference comparison' to the referenceImages concept; baseline 3 is appropriate when the schema does the heavy lifting.

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 clear compound verb+resource: capture and audit a real localhost web UI in one browser pass, optionally comparing FigCraft references and returning prioritized issues. The phrase 'in one browser pass' implicitly distinguishes it from the granular siblings (capture_ui_screenshots, compare_ui_screenshots, audit_ui_page), though it never names them.

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 prerequisite 'Requires project-local Playwright' is a useful usage gate, and 'optionally compare' flags conditional behavior. But there is no explicit guidance on when to choose this over the dedicated capture/compare/audit siblings, leaving the primary routing decision to inference.

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