analyze_hover_census

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

Annotations already cover the safety profile (readOnly, non-destructive, open-world, non-idempotent), so the bar is lower. The description adds genuinely useful behavior beyond them: the ≤20 element sampling cap and the live-page/URL scope. It doesn't mention timing, rate limits, or failure modes, keeping it at 4.

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?

Front-loaded with the core operation, then the use case, then scope — every clause carries information. The trailing "does not fetch awwwards.com" note is slightly cryptic but functions as a useful scope boundary; near-optimal sizing overall.

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 steps in by describing the return content (counts, sampled elements, changed properties with duration/easing), which is exactly what an agent needs. It omits any note on result format or limits on the count output, so not quite complete.

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 75%, so the schema already explains url, viewport, and reducedMotion. The description adds no parameter-level detail (e.g., what waitStrategy does or when to choose networkidle), 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?

States a specific verb and resource — a ":hover interaction census" — and enumerates exactly what it produces: hover rule counts, up to 20 sampled interactive elements, and CSS properties that change with duration/easing. This distinguishes it clearly from siblings like analyze_scroll_map or analyze_page_structure that census different interaction axes.

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?

"Use it to reproduce micro-interactions and verify interaction-state coverage" gives a clear when-to-use rationale, and the scope note (runs on any URL, does not fetch awwwards.com) bounds applicability. It stops short of naming an explicit alternative (e.g., a motion or scroll analyzer) or a when-not condition, so it falls under 5.

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