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

The annotations already establish that this is safe, read-only, open-world, and idempotent, and the description adds meaningful behavioral detail beyond that: it uses headless Chromium and real getBoundingClientRect when a url is provided, is fully non-rendering in elements mode, requires headless Chromium for url mode, and returns a sorted worst-first fix table. It describes the output table fields in enough detail without an output schema.

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 dense but efficient: it lists the affected element selectors, the output columns, the CRUCIAL behavior difference between the two modes, and the default threshold. There is no filler or repetition from the schema. Every sentence contributes a distinct piece of information an agent needs.

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 tool with no output schema and only annotations, this description covers everything: what gets audited, what the audit emits, what measurements mean, the minimum-size default, the two accepted input modes, and the environmental requirement (headless chromium for url). It is fully actionable for an agent deciding whether to call the tool and how to invoke it.

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 already 3. The description adds extra value by explaining that url triggers rendering and measurement, while elements is a pure no-browser mode, and by explicitly stating the 44px default that minSize controls. This goes beyond what the schema says without being overly verbose.

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 names the specific audit standard (WCAG 2.5.5 / Apple 44pt), the exact resource being audited (web interactive elements), and the concrete output (per-element fix table). It clearly differentiates this from the many sibling audit tools because it is specifically about tap-target dimensions and proposes CSS fixes.

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 gives clear guidance on when to use each input mode: pass a url for real headless-chromium rendering plus measurement, or pass pre-collected elements[] for a pure, no-browser snapshot audit. It does not explicitly state when to choose this over sibling alternatives like audit_ios_a11y or audit_page, so it stops just short of full routing guidance.

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