rtl_audit_css

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

No annotations are provided, so the description carries the full burden. It usefully discloses that the tool only detects and suggests (implying non-mutating behavior) and lists the covered pattern families, but it says nothing about return format, whether comments/strings are excluded, severity levels, or false-positive handling.

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 front-loaded sentence: verb and input types come first, then the detection scope, then the action. The parenthetical pattern list is long but earns its place by concretely defining 'LTR-only patterns'. No filler or restatement of the title.

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 and no annotations, the description is the only source of behavior, and while it covers what is detected it never describes the shape of the result (findings list, line numbers, per-file grouping) or any limits on input size. For a one-parameter audit tool this is close to sufficient but leaves the agent guessing about the response.

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?

The single 'code' parameter has 0% schema description coverage, so the description must compensate. It partially does by clarifying that the parameter accepts CSS/HTML/JSX/Tailwind text, which is genuinely useful input-format guidance. It does not, however, say whether code is a file path, raw string, or snippet size limits, leaving real ambiguity.

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 opens with a precise verb+resource ('Scan CSS/HTML/JSX/Tailwind text') and enumerates the exact pattern classes it targets (margin-left, ml-4, text-align:left, float:left, forced ltr, directional icons). It also states the outcome ('suggest logical replacements'), so the agent knows it is an analysis tool rather than a mutator. It does not explicitly differentiate itself from the sibling rtl_convert_css, which is the main gap.

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 word 'suggest' implies a read-only audit step versus the mutating rtl_convert_css/rtl_convert_tailwind siblings, so usage can be inferred. However, there is no explicit when-to-use/when-not guidance, no statement of ordering (audit before convert), and no sibling named. Adequate but clearly improvable given three closely related RTL siblings.

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