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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds the pricing ($0.20 per page), the heuristic nature ('fast heuristic'), and the specific checks performed. This goes beyond annotations without contradicting them.

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 two concise sentences: the first states purpose and checks, the second gives usage context and pricing. It is front-loaded and contains no fluff.

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?

The description is mostly complete for a simple tool with annotations covering safety and an output schema available. However, the ambiguity around the 'source' parameter (URL vs. raw HTML) is a notable gap that could mislead an agent. The tool's simplicity and schema help, but this key detail 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?

The input schema has one parameter 'source' with two variants (url or html), but the description says 'public HTML' which implies URL-only, failing to clarify that raw HTML can be passed directly. With schema description coverage at 0%, the description needed to explain the parameter options, but it does not.

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 clearly states the tool checks public HTML for specific accessibility failures, listing concrete checks (missing image text, labels, page language, headings, link names). This distinguishes it from sibling tools like openapi_agent_auditor or dependency_risk_scanner, which target different domains.

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 provides an explicit usage context: 'Use when HTML needs a fast heuristic accessibility review before publishing.' It gives a clear scenario but does not mention alternatives or exclusions, so it misses a full comparison with other audit tools.

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