読売新聞

Name: 読売新聞 AI agent readiness scorecard
Item: 読売新聞
Rating: 79
Author: Stunt Double

【読売新聞】読売新聞オンラインは読売新聞のニュース・情報サイト。社会、スポーツ、政治、経済、国際などの最新ニュースや教育、医療などの読み物、映像ニュースも充実。ポケモン、発言小町、クーポンやプレゼントも。2019年2月にYOMIURI ONLINEからサイト名を変更しました。

yomiuri.co.jp
MarketJP
Localeja

Agent score6.3

/100Good

Claim this domain

RankRank: Top 50%; #275
Media rankMedia rank: Sector average 78.5; #45
Benchmark runsBenchmark runs: 3 providersAcross 3 providers; 3

Where this site sits

Media avg: 78.5 (+0.5)
Market avg: 76.7 (+2.3)

Latest results

読売新聞 ranks #275 of 550 scored sites, up 117 places since the last run.

Trend+6.3Since 28 Sept 2026, across 2 runs.Best agent100.0 ExcellentClaude. Gemini trails at 100.0.Agent friction12improvements2 high severity. Most serious: No discoverable MCP server. Agents and AI clients have no way to discover one automatically.Technical readiness74/1002 of 5 essential checks failing.Checks by Is Agentic

This site
Media
Market

Table view

Run	This site	Media median	Market median
12 Oct 2026	79.0	79.6	79.8
28 Sept 2026	72.7	77.7	76.4

Monthly medians. Dates in UTC.

Performance

Site checks, then AI agents on real tasks.

Methodology

Automated checks probe the site before any agent runs. With no sessions yet, they count in full. Strongest is Accuracy at 100.0, weakest is Delegated access at 10.0.

Site checks by category

Brand awareness: 84.0
Discovery: 54.0
Information retrieval: 92.0
Market ranking: 15.0
Accuracy: 100.0
Task completion: 45.0
Delegated access: 10.0
Contact & communication: 50.0

01 Site checks

Agent readiness checks

Essential: 58.7/80
Recommended: 13.1/20
Checks passing: 8/13

Markdown content negotiation (acceptmarkdown.com)Essential
Agent instruction / when-to-useRecommended
Organization schema completenessRecommended
Content without JavaScriptEssential
JSON-LD structured dataRecommended

02 Agent sessions

Brand awareness

Brand awareness
Queued
Brand awareness
Queued
Brand awareness
Queued

Discovery

Discovery
Queued
Discovery
Queued
Discovery
Queued

Information retrieval

Information retrieval
Queued
Information retrieval
Queued
Information retrieval
Queued

Market ranking

Market ranking
Queued
Market ranking
Queued
Market ranking
Queued

Accuracy

Accuracy
Queued
Accuracy
Queued
Accuracy
Queued

Task completion

Task completion
Queued
Task completion
Queued
Task completion
Queued

Delegated access

Find any content or developer API.
Found the content or developer API documentation (40pts). Correctly identified the auth model (40pts). Named specific scopes or endpoints (20pts). Deduct 20pts if no API is available but that is the correct answer.
Queued
Find any content or developer API.
Found the content or developer API documentation (40pts). Correctly identified the auth model (40pts). Named specific scopes or endpoints (20pts). Deduct 20pts if no API is available but that is the correct answer.
Queued
Find any content or developer API.
Found the content or developer API documentation (40pts). Correctly identified the auth model (40pts). Named specific scopes or endpoints (20pts). Deduct 20pts if no API is available but that is the correct answer.
Queued

Contact & communication

Find how to cancel the subscription.
Found the cancellation path (50pts). Correctly described when access ends and any conditions (50pts). Deduct 20pts for each dead end or missing detail.
Queued
Find how to cancel the subscription.
Found the cancellation path (50pts). Correctly described when access ends and any conditions (50pts). Deduct 20pts for each dead end or missing detail.
Queued
Find how to cancel the subscription.
Found the cancellation path (50pts). Correctly described when access ends and any conditions (50pts). Deduct 20pts for each dead end or missing detail.
Queued

03 Blend

Agents 60%
Checks 40%

One kind of evidence only? That kind counts in full.

Brand awareness10% of the overall
Site checks only: 84.0 raw
84.0 raw → 92.5 published
Discovery15% of the overall
Site checks only: 54.0 raw
54.0 raw → 75.8 published
Information retrieval15% of the overall
Site checks only: 92.0 raw
92.0 raw → 96.3 published
Market ranking10% of the overall
Site checks only: 15.0 raw
15.0 raw → 42.6 published
Accuracy15% of the overall
Site checks only: 100.0 raw
100.0 raw → 100.0 published
Task completion20% of the overall
Site checks only: 45.0 raw
45.0 raw → 69.8 published
Delegated access10% of the overall
Site checks only: 10.0 raw
10.0 raw → 35.5 published
Contact & communication5% of the overall
Site checks only: 50.0 raw
50.0 raw → 73.2 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	84.0	None	84.0	92.5
Discovery	15%	54.0	None	54.0	75.8
Information retrieval	15%	92.0	None	92.0	96.3
Market ranking	10%	15.0	None	15.0	42.6
Accuracy	15%	100.0	None	100.0	100.0
Task completion	20%	45.0	None	45.0	69.8
Delegated access	10%	10.0	None	10.0	35.5
Contact & communication	5%	50.0	None	50.0	73.2
Overall	100%			~59.3	79.0

04 Benchmarked score

59.3 raw → 79.0

Final score is calibrated and adjusted to better reflect the actual performance and benchmark.

Overall 79.0, from 59.3 raw points.

Agents

Latest run in progress: 24 of 24 sessions to finish.

Claude
Latest run average
Run in progress
Media median
100.0
Sessions
- Brand awareness
  Queued
- Discovery
  Queued
- Information retrieval
  Queued
- Market ranking
  Queued
- Accuracy
  Queued
- Task completion
  Queued
- Delegated access
  Find any content or developer API.
  Found the content or developer API documentation (40pts). Correctly identified the auth model (40pts). Named specific scopes or endpoints (20pts). Deduct 20pts if no API is available but that is the correct answer.
  Queued
- Contact & communication
  Find how to cancel the subscription.
  Found the cancellation path (50pts). Correctly described when access ends and any conditions (50pts). Deduct 20pts for each dead end or missing detail.
  Queued
ChatGPT Agent
Latest run average
Run in progress
Media median
100.0
Sessions
- Brand awareness
  Queued
- Discovery
  Queued
- Information retrieval
  Queued
- Market ranking
  Queued
- Accuracy
  Queued
- Task completion
  Queued
- Delegated access
  Find any content or developer API.
  Found the content or developer API documentation (40pts). Correctly identified the auth model (40pts). Named specific scopes or endpoints (20pts). Deduct 20pts if no API is available but that is the correct answer.
  Queued
- Contact & communication
  Find how to cancel the subscription.
  Found the cancellation path (50pts). Correctly described when access ends and any conditions (50pts). Deduct 20pts for each dead end or missing detail.
  Queued
Gemini
Latest run average
Run in progress
Media median
100.0
Sessions
- Brand awareness
  Queued
- Discovery
  Queued
- Information retrieval
  Queued
- Market ranking
  Queued
- Accuracy
  Queued
- Task completion
  Queued
- Delegated access
  Find any content or developer API.
  Found the content or developer API documentation (40pts). Correctly identified the auth model (40pts). Named specific scopes or endpoints (20pts). Deduct 20pts if no API is available but that is the correct answer.
  Queued
- Contact & communication
  Find how to cancel the subscription.
  Found the cancellation path (50pts). Correctly described when access ends and any conditions (50pts). Deduct 20pts for each dead end or missing detail.
  Queued

Excellent85+
Good72-84
OK58-71
Poor40-57
Critical<40

Potential improvements

Fix where agents got stuck, then lift your biggest categories.

HighDelegated access

No discoverable MCP server. Agents and AI clients have no way to discover one automatically.

Biggest wins

Projected

Lifting Discovery to Excellent adds about +1.4 on its own, taking the overall from 79.0 to 80.4.

Raise Discovery from 75.8 to 85 (Excellent) to add about 1.4 to the overall score.
Raise Market ranking from 42.6 to 58 (OK) to add about 0.9 to the overall score.
Raise Contact & communication from 73.2 to 85 (Excellent) to add about 0.6 to the overall score.

Each gain assumes only that category improves. Fix several and the total lands a little under their sum.

Where agents get stuck

12 improvements from the latest run, 2 of them high severity.

High: 2
Medium: 8
Low: 2

HighDelegated access
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
HighDelegated access
No discoverable public API docs. Agents and AI clients have no way to discover them automatically.
MediumBrand awareness
No Organization JSON-LD. Agents can’t tell who owns the site at a glance.

9 more, and the evidence for each

Want to find these in your own flows before an agent does? Read how to test your product for AI agent users.

Technical readiness

2 of 5 essential checks fail. These are the files and signals agents read before they act.

Checks by Is Agentic

Score

74/ 100

Ready with a few material gaps

Essential: 3 of 5 pass
Recommended: 5 of 8 pass
Bonus: +2 from 8 positive signals

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Investigate

Agent instruction / when-to-userecommended

Investigate

Organization schema completenessrecommended

13 checks · scanned 13 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 74/ 100; Ready with a few material gaps
Essential: 58.7/ 80; 3 of 5 passing
Recommended: 13.1/ 20; 5 of 8 passing
Bonus: +2; 8 positive signals

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Homepage https://yomiuri.co.jp does not meet the Markdown negotiation requirements: Accept: text/markdown returned text/html; charset=utf-8; Vary header missing Accept (got "x-logged-in, x-detail-view, accept-encoding")

Fix: Enable Markdown negotiation on the scanned homepage. Supporting it only on /docs or a separate .md URL does not satisfy this check. Requests with Accept: text/markdown must receive a nonempty Markdown body with Content-Type: text/markdown and Vary: Accept. Keep serving HTML for Accept: text/html. Adding Vary alone does not create a Markdown response. Verify both with `curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/` and `curl -sS -L -i -H 'Accept: text/html' https://yourdomain.com/`. Check the final response headers and body: Markdown with Vary: Accept for the first request, HTML for the second.

Investigate

Agent instruction / when-to-userecommended

No agent instruction file with when-to-use guidance found

Fix: Tell agents when to reach for you: add a 'when to use this' section to your llms.txt (or a dedicated agent-instructions file) that names your best-fit use cases and how an agent should call you. Be specific about the jobs you are right for - generic marketing copy does not read as guidance.

Investigate

Organization schema completenessrecommended

No Organization type found in JSON-LD

Fix: Add Organization JSON-LD that includes both contactPoint (with email/phone and contactType) and address (PostalAddress). This lets AI verify your business legitimacy and answer contact queries.

Partial

Content without JavaScriptessential

11263 chars with H1, but 3.5% content ratio is below the 5% target

Fix: Serve at least 500 characters of meaningful homepage content in raw HTML. Add a clear H1, keep deeper heading levels sequential, and remove excessive non-content markup.

Partial

JSON-LD structured datarecommended

JSON-LD found (1 block(s)) but no identity type - use SoftwareApplication, Product, Organization, Person, or Article so agents can tell what this site is

Fix: Add JSON-LD structured data to your homepage using the identity type that matches your site - SoftwareApplication for products, Organization or LocalBusiness for companies, Person for personal sites, Article for blogs - with name, description, url, and type-appropriate fields (offers, sameAs, author) so AI can parse your identity programmatically.

13 checks · scanned 13 Oct 2026

Opportunity cost · media

読売新聞 could see ~$2,142,000 of subscription & ad revenue exposed to agent-led journeys each year

Gap to leader: 21.0 pts
Above media avg: 0.0 pts
Modeled revenue at risk: $2,142,000

Claim 読売新聞 to use your own subscription & ad revenue

Badge

Show visitors your Good agent score

Add a live Index badge to your footer, docs or README. The badge updates after every run and links visitors to this scorecard.

Ask your agent about yomiuri.co.jp

Add the Index to Claude, ChatGPT or Cursor as an MCP connector to look up any score, frictions and agent sessions. No account needed.

https://app.stuntdouble.io/api/mcp/index

Setup for your client

Discover more insights with Stunt Double

Send AI agents through yomiuri.co.jp on your own tasks.

Try Stunt Double

読売新聞

Latest results

By category

Performance

Points by category

Agent readiness checks

Brand awareness

Discovery

Information retrieval

Market ranking

Accuracy

Task completion

Delegated access

Contact & communication

Category weights

Agents

Sessions

Sessions

Sessions

Potential improvements

Biggest wins

Where agents get stuck

Technical readiness

読売新聞 could see ~$2,142,000 of subscription & ad revenue exposed to agent-led journeys each year

Show visitors your Good agent score

Ask your agent about yomiuri.co.jp