Check a public page for deterministic HTML accessibility problems and return actionable WCAG-oriented findings.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Structured Accessibility audit result | |
| meta | Yes | ||
| service | Yes | ||
| version | Yes | ||
| request_id | Yes | Unique request identifier |
Changes observed during successful MCP inspections.
Output schema / properties / data / properties / urlAdded value: +{
+ "type": "string"
+}Output schema / properties / meta / properties / next_actions / items / properties / checkout_pathAdded value: +{
+ "pattern": "^/try/",
+ "type": "string"
+}Output schema / properties / meta / properties / next_actions / items / properties / executes_automaticallyAdded value: +{
+ "const": false,
+ "type": "boolean"
+}Output schema / properties / meta / properties / next_actions / items / properties / handoff_pathAdded value: +{
+ "description": "Free full contract and spend-capped command handoff; reading it does not execute or purchase the follow-up.",
+ "pattern": "^/catalog/",
+ "type": "string"
+}Output schema / properties / meta / properties / next_actions / items / properties / handoff_payment_requiredAdded value: +{
+ "const": false,
+ "type": "boolean"
+}Output schema / properties / meta / properties / next_actions / items / properties / maximum_atomic_usdcAdded value: +{
+ "pattern": "^[1-9][0-9]*$",
+ "type": "string"
+}Output schema / properties / meta / properties / next_actions / items / properties / sample_pathAdded value: +{
+ "pattern": "^/samples/",
+ "type": [
+ "string",
+ "null"
+ ]
+}Output schema / properties / meta / properties / next_actions / items / requiredPrevious value: -[
- "service",
- "title",
- "reason",
- "method",
- "path",
- "price",
- "input_template",
- "use_output",
- "authorization_required"
-]New value: +[
+ "service",
+ "title",
+ "reason",
+ "method",
+ "path",
+ "price",
+ "input_template",
+ "use_output",
+ "handoff_path",
+ "checkout_path",
+ "sample_path",
+ "maximum_atomic_usdc",
+ "handoff_payment_required",
+ "executes_automatically",
+ "authorization_required"
+]Output schema / properties / meta / properties / next_actionsAdded value: +{
+ "description": "Optional separately priced follow-up calls. Each action requires a new payment challenge and explicit buyer authorization.",
+ "items": {
+ "properties": {
+ "authorization_required": {
+ "const": true,
+ "type": "boolean"
+ },
+ "input_template": {
+ "description": "Client-side template only: $request refers to the original input, $result to this response, and $json(...) serializes its argument. The server does not execute the follow-up.",
+ "type": "object"
+ },
+ "method": {
+ "const": "POST",
+ "type": "string"
+ },
+ "path": {
+ "pattern": "^/v1/",
+ "type": "string"
+ },
+ "price": {
+ "pattern": "^\\$[0-9]+",
+ "type": "string"
+ },
+ "reason": {
+ "type": "string"
+ },
+ "service": {
+ "type": "string"
+ },
+ "title": {
+ "type": "string"
+ },
+ "use_output": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "service",
+ "title",
+ "reason",
+ "method",
+ "path",
+ "price",
+ "input_template",
+ "use_output",
+ "authorization_required"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / meta / requiredPrevious value: -[
- "duration_ms",
- "cached",
- "sources",
- "warnings"
-]New value: +[
+ "duration_ms",
+ "cached",
+ "sources",
+ "warnings",
+ "next_actions"
+]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 meaningful context about the deterministic nature of findings and their WCAG orientation, which complements the 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 a single, well-structured sentence. It is front-loaded with the verb and purpose, and every word contributes meaning without waste.
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 the simple tool signature (one parameter), rich annotations, and presence of an output schema, the description sufficiently covers the core purpose and output type. It does not need to explain return values because an output schema exists. Minor gap: no mention of typical use cases beyond the generic description, but this is not critical for such a focused tool.
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 0%, so the description must compensate. It adds the semantic constraint that the URL must be a 'public page', which is useful beyond the schema's format/type. However, it does not elaborate on other parameter aspects like redirects or authentication, leaving some gaps.
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 action ('Check'), the target resource ('a public page'), and the specific focus ('deterministic HTML accessibility problems'), with an outcome ('actionable WCAG-oriented findings'). This distinguishes it from sibling tools like web.security-audit and web.seo-audit by pinpointing accessibility.
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 implies clear usage context: use this tool when you need an accessibility audit of a public page. However, it does not explicitly mention alternatives or when not to use it (e.g., for private pages or comprehensive audits like web.full-audit).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.