Skip to main content
Glama

run_verification_suite

Test a proposed accessibility patch (search/replace and CSS selector) against a live URL in a sandboxed browser before committing. Compares axe-core scores before and after, returns score delta and rule pass.

Instructions

[audit] PRE-deploy patch verification: test a proposed patch (search/replace + CSS selector) against a live URL in a sandboxed browser BEFORE you commit. Runs before/after axe-core, returns score delta + rule pass. vs verify_fixes: that's POST-deploy URL-vs-baseline comparison; this is patch-vs-live in isolation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
patch_idNoID of a previously generated patch to verify (not yet supported)
patch_contentNoInline patch content for verification
urlYesURL to verify the patch against — must be a live, reachable page (the verifier renders it in a headless browser).
selectorYesCSS selector of the element that had the original issue. HOW TO GET IT: (1) call get_findings(audit_id, finding_id) — returns finding.selector directly; (2) or call explain_finding(finding_id) which includes the element selector and context; (3) or read finding.node.target[0] from an axe-core finding. Required — the verifier scopes the before/after check to this element.
rule_idNoAxe-core rule ID to check is fixed (e.g., 'color-contrast', 'button-name', 'link-name'). When omitted, all rules on the selector element are checked. Strongly recommended for precise pre-deploy verification — source it from `finding.rule` in the audit response.
timeout_msNoVerification timeout in milliseconds (default: 60000, max: 120000)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

Discloses behavioral traits: runs in a sandboxed browser, performs before/after axe-core checks, returns score delta and rule pass. Annotations indicate non-destructive and non-read-only; description adds meaningful process details without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (3-4 sentences), front-loaded with the key action, and every sentence adds value. No superfluous wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers main use case, parameter sourcing, and distinguishes from an alternative. With an output schema present, the description does not need to detail return format extensively. However, it could mention error handling or prerequisites for completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description significantly augments the input schema by providing practical guidance for obtaining the selector (from get_findings, explain_finding, or finding.node.target), explains rule_id sourcing, and clarifies constraints like URL must be live. All 6 parameters are covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as pre-deploy patch verification, specifying it tests a proposed patch against a live URL in a sandboxed browser. It distinguishes from verify_fixes (post-deploy comparison) and uses specific verbs and resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (pre-deploy, before commit) and contrasts with the alternative verify_fixes (post-deploy). Provides clear context for selection.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/VertaaUX/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server