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

Goes well beyond the readOnly/openWorld/destructive=false annotations: discloses the up-to-12-stylesheet fetch limit, browser defaults for form controls, text-width guessing, margin/gap and li > a handling, neighbor detection, the full status enum (fail-estimate, under-24-isolated, under-24-spaced, inline, unknown, ok), and an explicit list of what it does not handle (state/sibling/structural selectors, transforms, container queries, script-set sizes). This is exactly the behavioral context annotations cannot carry.

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 purpose, input modes, and limits are front-loaded, and the closing sentence on non-support preempts confusion. The middle sentence on matching rules, size sources, and neighbor detection is dense and long, but nearly all of it is load-bearing detail about how the estimate is produced.

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 carries the burden and does so: it explains output grouping by element kind and defines every status value an agent will see. Combined with the stated limitations, an agent has enough to call this correctly and interpret its results.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: `url` covers a page plus up to 12 stylesheets, `viewport` defaults to 390 and drives media-query selection, and `html`+`css` is presented as the alternative input mode. That is genuine semantic enrichment of the parameters.

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?

Names a precise verb+resource ('Static estimate of the rendered size of interactive elements') and enumerates the element set (a, button, input, select, textarea, summary, role-based, onclick) plus the standards it targets (WCAG 2.5.8, 44px). The 'static estimate' framing implicitly separates it from the rendered-measurement path, which it points to via the Puppeteer snippet.

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 call conditions: pass `html` and `css`, or a public `url`; `viewport` selects media queries. It also states plainly that the result is an estimate (with a rendered alternative), which is real usage guidance. It stops short of explicitly naming the sibling `check_touch_targets` or stating when to prefer it.

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