developer.gemini.com agentic web readiness

B Manifest validity: 33% (1/3 valid, 10 errors, 7 warnings) · Surface score 41 (coverage 30 + breadth 6 + conformance 5). 4 standards observed across 3 of 9 steps; 3 manifests present (+ robots.txt), 10 errors, 7 warnings. Checked 2026-10-25 23:39:35 UTC. This grades the agent-facing files published at developer.gemini.com, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/developer.gemini.com.svg) · JSON · Markdown · Re-check now

Coverage by step

Manifests

{
  "name": "Developer",
  "description": "Developer and what it offers to agents",
  "version": "1.0.0",
  "provider": {
    "organization": "Developer",
    "url": "https://developer.gemini.com/"
  },
  "documentationUrl": "https://developer.gemini.com/AGENTS.md",
  "supportedInterfaces": [
    {
      "url": "https://developer.gemini.com/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    }
  ],
  "url": "https://developer.gemini.com/a2a",
  "protocolVersion": "1.0",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "answer",
      "name": "Answer questions",
      "description": "Answer questions about Developer.",
      "tags": [
        "qa"
      ],
      "examples": [
        "What does Developer do?"
      ]
    }
  ],
  "securitySchemes": {},
  "securityRequirements": []
}

{
  "$schema": "https://schemas.agentskills.io/discovery/0.2.0/schema.json",
  "skills": [
    {
      "name": "developer",
      "type": "skill-md",
      "description": "Developer and what it offers to agents",
      "url": "https://developer.gemini.com/.well-known/agent-skills/developer/SKILL.md",
      "digest": "sha256:0000000000000000000000000000000000000000000000000000000000000000"
    }
  ]
}

What an agent can call

• A2A agent Gemini Developer Platform Agent at https://developer.gemini.com/rest-api/rest-api, skills: Spot & Derivatives Trading, Market Data & Tickers, Fund & Account Management
• llms.txt: Gemini Developer Platform API Documentation, 335 links, llms-full.txt present
• robots.txt AI policy: no AI crawler tokens named; unlisted crawlers allowed

Standards observed

• Agent2Agent Protocol https://developer.gemini.com/.well-known/agent-card.json
• llms.txt https://developer.gemini.com/llms.txt
• Agent Skills https://developer.gemini.com/.well-known/agent-skills/index.json
• Markdown for Agents https://developer.gemini.com/

Cheapest next steps

1. Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch (emerging spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "ard", "domain": "developer.gemini.com"}))
2. AGENTS.md: instructions for coding agents working on or with the site
   Generate starter /AGENTS.md for developer.gemini.com

   # Developer for agents
   
   Developer and what it offers to agents
   
   ## Read the data, not the HTML
   - Index: https://developer.gemini.com/llms.txt
   - API description: https://developer.gemini.com/openapi.json
   - Discovery catalog: https://developer.gemini.com/.well-known/ard.json
   
   ## Calling
   - MCP server (Streamable HTTP): https://developer.gemini.com/mcp
   - Rate limits and authentication: describe them here
   
   ## Conventions
   - How to cite or attribute content
   - What not to do (no scraping of /account/, no automated sign-ups, etc.)
   
   Contact: security@developer.gemini.com
   

3. api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs: an RFC 9727 linkset pointing at your OpenAPI description (conditional spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "api-catalog-rfc9727", "domain": "developer.gemini.com"}))

Agent pre-flight & practical readiness

Preferred mode: a2a (fallback llms_txt). Send the task to the A2A agent endpoint named in the card. Use the card's skills instead of crawling pages.

Fetch: POST https://developer.gemini.com/rest-api/rest-api Send an A2A message to this agent endpoint. The card lists the skills.

Practical readability: exa_parsable yes, markdown negotiation yes, render markdown_native, HTML quality high, first content at byte 0.

AI crawler posture: open_to_all · Assistant access: OpenAI allowed, Anthropic allowed, Google allowed, Perplexity allowed, Exa allowed.

Readiness subscores: reach 20/20, readability 30/30, capabilities 12/35, conformance 5/15, total 67/100, grade A.

How the grade is made

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). Lifecycle grade: A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Strict 100-point composite (subscores.total_100 / subscores.grade_100): reach_and_policy (20) + readability (30) + capabilities (35) + conformance (15), where A+ >= 80, A >= 65, B >= 45, C >= 28, D >= 15. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules