analyze_coverage
ClaudeReport observation coverage for testable controls only. This is not requirements coverage. Page and form observations are excluded from the percentage.
Overview
CloudRoots Functional Testing works like a QA engineer for any public web page. Give it a URL and it reads the page's forms, fields, required flags, length and number limits, dropdown options, buttons and links. It then writes functional, negative and boundary test cases with realistic synthetic data. Each case is scored, duplicates are removed, and each case says whether it was inferred from the page or verified by a real request. It can also check every link on the page and report the real HTTP status. It can audit the page's title, meta description, headings, image alt text, form labels, HTTPS and security headers. Results export to Excel, Word, CSV, Playwright, Gherkin, Jira, GitHub, TestRail or Xray through a private download link that expires after 30 minutes. The public tools are read-only. They never click, submit forms, sign in or pay, and they refuse private and internal network addresses. No account is needed.
Tools
audit_page
ClaudeFetch a public page and check title, meta description, lang, viewport, h1, canonical, image alt text, form labels, link text, duplicate ids, HTTPS and security headers. Returns findings plus observed_fact test cases. Read-only: it does not click, submit, pay, or delete.
check_links
ClaudeRequest each unique link on a public page with a real GET and report the HTTP status, redirects and timing. Returns verified runtime results (basis verified_runtime_result), not inferences. Same-origin links are checked first. Read-only: it does not click, submit, pay, or delete.
compare_observations
ClaudeCompare observations from an earlier inspect_website run with a newer one. Lists controls that were added, removed, or changed (required, limits, options, labels) and the existing test cases that need re-running. Use it for regression checks after a release.
detect_duplicates
ClaudeFind exact and semantic duplicates. Cases for different targets are never duplicates, even when the wording is similar.
export_report
ClaudeBuild a downloadable .xlsx (Summary, Test Cases, Observations sheets), .docx, .csv, Playwright .spec.ts, or Gherkin .feature file from observations and test cases. Over HTTP it returns a downloadUrl valid for 30 minutes; over stdio it saves the file and returns savedPath.
generate_boundary_cases
ClaudeBuild concrete boundary values from one observation's min, max, minLength, or maxLength. If no limit was observed, returns EMPTY instead of a generic sentence.
generate_journeys
ClaudeBuild end-to-end journeys from observations: walk the main navigation, follow each call to action, complete a form with valid data, refuse a bad email, refuse an empty form, open and close a dialog. Each journey is a list of steps with expectations. Nothing runs yet.
generate_report
ClaudeSummarize observations, validation, quality, duplicates, coverage, and destructive cases. Read-only: it does not click, submit, pay, or delete.
generate_test_cases
ClaudeTurn observations into functional, negative, and boundary cases with concrete synthetic data. Read-only: it does not click, submit, pay, or delete. Empty input returns a message, not a silent empty list.
inspect_website
ClaudeFetch public HTML and return observed controls and constraints. Read-only: it does not click, submit, pay, or delete. Does not execute forms. Private networks and non-http(s) URLs are blocked.
review_test_cases
ClaudeMark cases PENDING, or NEEDS_EDIT when they score below the threshold. This tool cannot approve or reject.
score_test_case
ClaudeScore completeness, expected-result text, evidence honesty, and safety on a 1-5 rubric. MIN_QUALITY_SCORE (default 3.5) sets meetsThreshold.
validate_test_case
ClaudeCheck structure, evidence, honesty of basis, and destructive-action approval. Returns PASS, FAIL, or NEEDS_REVIEW. Malformed cases return INVALID_TEST_CASE instead of crashing.
