Audit layout across screens

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely useful behavior: the severity taxonomy (high/medium/low/info) and the semantic of viewport.deviceWidthPx vs layoutWidthPx as the responsiveness test. It stops short of runtime cost or how heavy a 12-device run is.

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?

Three tight paragraphs with the core purpose front-loaded, then severity definitions, then the usage/handoff guidance. Dense but every sentence carries information; slightly long but no filler.

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 14-parameter, no-output-schema tool, the description adequately explains what is reported, the severity levels, and the responsiveness criterion, so an agent can interpret results. It could say more about runtime expectations across many devices, but nothing essential is missing.

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%, so the schema already documents all 14 parameters, establishing the baseline of 3. The description corroborates a few (media queries, overflow selector) and clarifies output semantics, but adds little parameter-level meaning beyond the schema.

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+resource: opens a URL across multiple screens and reports only responsive problems (overflow, clipped text, tap targets, viewport meta, media queries). It explicitly excludes images and names the failing-device handoff to screenshot_on, so an agent can distinguish it from siblings without opening a schema.

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?

Gives clear when-to-use (verifying a redesign, finding broken breakpoints) and a concrete follow-up alternative (screenshot_on on the failing device). It does not address the session-based siblings (open_responsive_session/observe_responsive_session), so the alternative routing is incomplete but the positive guidance is strong.

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