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

Adds context well beyond the annotations: confirms read-only/offline behavior ('nothing is rendered or run, stored or logged'), and openly discloses the heuristic weakness of icon advice ('by name and follows common guidance, so treat it as convention'). That caveat is exactly the kind of epistemic transparency an agent needs before trusting the output.

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 purpose and the input instruction, then a dense enumeration that is long but content-bearing. The list of flagged conditions is extensive yet each item is a real check, though the run-on construction could be tightened with grouping.

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?

No output schema exists, and the description compensates by describing the return shape: declarations paired with their logical replacements, plus flags for locale-specific issues and icon-by-name guidance. An agent knows what it will get back and the limits of that output.

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?

Only one parameter with 100% schema coverage, so the schema carries the semantics; the description restates the accepted formats (HTML with style blocks, or CSS) which marginally reinforces rather than extends the schema. Baseline 4 applies for a single well-documented parameter.

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 ('static review for right-to-left languages') and then enumerates exactly what it inspects (margin/padding/float/text-align declarations, bidi overrides, control characters, missing lang/dir, directional icons). The scope 'static' and 'pasted source only' makes it distinguishable from siblings like localisation_readiness or check_cjk_line_breaking without opening the 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?

It tells the agent what to pass ('HTML with styles, or CSS') but never states when to choose this over the nearby alternatives (localisation_readiness, stress_test_localisation, review_locale_picker, check_cjk_line_breaking). Usage is implied by the topic enumeration rather than by explicit routing guidance.

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