Audit a rendered URL

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint true, and destructiveHint false. The description adds context: it uses headless Chromium, is read-only (reinforcing safely), and lists concrete outputs (WCAG findings, DOM evidence, computed styles, contrast corrections). No contradictions.

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 a single sentence front-loaded with the primary action and outputs, then ends with 'Read-only.' Every part is essential and no filler. Excellent structure and brevity.

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?

Given 6 parameters (100% schema coverage), rich annotations, and no output schema, the description provides enough context for an AI agent to select and invoke the tool correctly. It covers inputs, behavior, and safety. Slight deduction because it doesn't mention pagination or error handling for invalid URLs, but overall complete.

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 description coverage is 100%, so baseline is 3. The description adds value beyond schema by summarizing the overall return structure (prioritized findings, evidence, contrast corrections), but doesn't detail individual parameter behaviors beyond what schema provides. Slight extra context earns a 4.

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 loads a page, runs axe-core, and returns prioritized WCAG findings with specific outputs like DOM evidence and computed styles. It distinguishes itself from siblings like audit_html and audit_file, which operate on different input types.

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 implicitly indicates usage for accessibility auditing of rendered URLs and mentions 'Read-only.' However, it does not explicitly contrast with siblings like check_contrast or explain_issue, nor does it specify when not to use this tool (e.g., for non-public pages or HTML fragments).

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