X scores 84/100 (Grade B), passing 11 of 22 checks (50%). The documentation is broadly accessible to AI agents but has 8 areas that could be improved to better serve automated tooling.
# Agent Score Fix Report — X URL: https://docs.x.ai/developers/tools/overview Score: 84/100 (Grade B) I need help improving the AI-readiness of the documentation at https://docs.x.ai/developers/tools/overview. Agent Score found 5 failing checks and 3 warnings. ## Failing Checks (5) - [content-discoverability] Llms Txt Size: llms.txt is 922,338 characters (exceeds 100,000 threshold; will be truncated by most agents) - [page-size] Page Size Html: 6 of 10 sampled pages convert to over 100K chars (max 662K, 50% boilerplate) - [page-size] Content Start Position: 1 of 10 sampled pages have content starting past 50% (worst 100%) - [observability] Markdown Content Parity: 2 of 9 pages have substantive content differences between markdown and HTML (avg 12% missing) - [observability] Cache Header Hygiene: 6 of 11 endpoints have aggressive caching or missing cache headers ## Warnings (3) - [content-discoverability] Llms Txt Valid: llms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.x.ai/llms.txt: No H1 heading found - [content-discoverability] Llms Txt Links Resolve: All links are external; 2/10 resolve (8 failed; may be bot-detection or rate-limiting) - [markdown-availability] Markdown Url Support: 8/10 sampled pages support .md URLs (80%); inconsistent support ## Fix Instructions For each issue above, please: 1. Analyze the documentation site at https://docs.x.ai/developers/tools/overview 2. Implement the specific fix 3. Verify the fix would cause the check to pass ### Common fixes: - **No llms.txt**: Create /llms.txt following https://llmstxt.org — list all doc pages in markdown format - **No .md URL support**: Configure your docs platform to serve pages at equivalent .md URLs (e.g. /docs/quickstart.md) - **No content negotiation**: Return markdown when request includes Accept: text/markdown header - **Large page size**: Reduce nav boilerplate, inline scripts, and repetitive markup - **No sitemap**: Generate /sitemap.xml listing all documentation URLs - **Auth walls**: Ensure docs pages return 200 without requiring login cookies or tokens - **No Last-Modified header**: Configure your server/CDN to include Last-Modified response headers - **Tab content hidden**: Ensure tabbed content is rendered in the HTML (not JS-only) so agents can read all variants ## Run afdocs Locally for More Detail To get deeper visibility into what's failing, run afdocs against your docs: npx afdocs https://docs.x.ai/developers/tools/overview --fixes --verbose - **--fixes**: Adds "Fix:" lines to the output for each warn/fail check with actionable remediation steps - **-v, --verbose**: Shows per-page details (specific URLs, character counts, error codes) for checks with issues — useful for per-URL visibility into what's failing
CHECK RESULTS
How your docs scored
markdown-content-parity2 of 9 pages have substantive content differences between markdown and HTML (avg 12% missing)
cache-header-hygiene6 of 11 endpoints have aggressive caching or missing cache headers
llms-txt-freshnessSitemap has 104 URLs but none are under the docs path prefix (/developers/tools/overview)
llms-txt-sizellms.txt is 922,338 characters (exceeds 100,000 threshold; will be truncated by most agents)
llms-txt-validllms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.x.ai/llms.txt: No H1 heading found
llms-txt-links-resolveAll links are external; 2/10 resolve (8 failed; may be bot-detection or rate-limiting)
llms-txt-existsllms.txt found at 1 location(s)
llms-txt-directivellms.txt directive found in all 9 sampled pages, near the top of content; 1 failed to fetch
llms-txt-links-markdownAll 81 links are external; cannot assess markdown support
page-size-html6 of 10 sampled pages convert to over 100K chars (max 662K, 50% boilerplate)
content-start-position1 of 10 sampled pages have content starting past 50% (worst 100%)
rendering-strategyAll 10 sampled pages contain server-rendered content
page-size-markdownAll 9 pages under 50K chars (median 11K, max 40K)
auth-gate-detectionAll 10 sampled pages are publicly accessible
auth-alternative-accessAll docs pages are publicly accessible; no alternative access paths needed
markdown-url-support8/10 sampled pages support .md URLs (80%); inconsistent support
content-negotiation9/10 sampled pages support content negotiation (90%)
tabbed-content-serializationNo tabbed content detected across 10 sampled pages
section-header-qualityNo tabbed content found; header quality check not applicable
markdown-code-fence-validityAll 864 code fences properly closed across 10 pages
http-status-codesAll 10 sampled pages return proper error codes for bad URLs
redirect-behaviorAll 1 redirect(s) across 10 sampled pages are same-host HTTP redirects
