AI Readiness AuditRef. APM-FB259769 · Confidential
Rosetta
An independent assessment of whether the Rosetta specification is ready for AI-assisted integration and autonomous agents, prepared for Coinbase.
86/100
AI-ready
Ready for AI-assisted builds.
Not ready for autonomous agents.
Not ready for autonomous agents.
Reach AI-ready by Phase 1; resolve all findings → 100 · AI-ready
F
D
C
B
A
86
055708085100
F · Not readyD · Significant gapsC · Needs workB · Mostly readyA · AI-ready
0
Critical blockers : no findings stop an operation group outright
509
Total instances: 0 critical, 5 high, 158 medium, 346 low
25
Rule groups across 4 pillars: 0 critical, 5 high sev. instances
Executive summary
Your API, Rosetta, scored 85.6 out of 100, reflecting strong compliance with standards and readiness for AI-assisted builds. The documentation readiness for AI stands at 82.1, while the SDK readiness is high at 89.8. However, the MCP readiness shows significant gaps at 68.5, and agents cannot make autonomous calls due to runtime limitations. Prioritizing improvements in MCP readiness will be essential for achieving full operational capability.
Readiness by pillar
AI-ready
86 / 100
FoundationThe spec itself
97/100
Standards Compliance
OpenAPI validity, structural correctness, specification conformance, and import linting: can machines trust your spec?
97AI-ready
Build Time ReadinessAI writes the code
86/100
Documentation Readiness for AI
Descriptions that say when to use an operation, examples that pin down every shape: whether an AI can learn the truth of your API from what you publish
82Mostly ready
SDK Readiness for AI
Clean types, predictable naming, correct formats: whether production-grade client code can be generated from your spec, by SDK pipelines and AI coding assistants alike
90AI-ready
Runtime ReadinessAgents make the calls
69/100
MCP Readiness
Whether your operations survive being turned into tools: distinct names, descriptions that carry what an agent must know, safe invocation semantics, auth, error recovery, and context budget
69Significant gaps
Score projection · what fixing each phase unlocks
Todaycurrent score
Phase 1fix highs
Phase 2+ fix mediums & lows
About this report. We evaluated the Rosetta specification against thousands of deterministic rules we have refined over twelve years of building API tooling, supplemented by AI-based analysis. Every finding is reproducible from the spec itself, scored consistently, and paired with a concrete fix.
What's at stake
Residual risks to monitor
No active failures, but elevated risks remain. Continued improvement will bring these into the managed band.
Foundation
The spec itself
97 / 100
Managed · Standards compliance
Empty Enumeration Item Violates Standards
You have one empty enumeration item in the Rosetta payments API, which can disrupt SDK generation and downstream integrations.
22→29
code quality score out of 40: the lift consumers achieve when the underlying spec is clean and standards-compliant
APIMatic Context Plugins research · Series B · June 2026
Build Time Readiness
AI writes the code
86 / 100
Managed · Documentation readiness for AI
Improve API documentation clarity: AI readers struggle with sparse and generic descriptions, which may lead to incorrect assumptions during builds
You can refine the documentation to ensure coding assistants accurately interpret the API's functionality.
74%
of developers name missing or unclear documentation as the top reason they abandon an API. AI readers are stricter: what a human would ask about, an AI assumes.
APIMatic Developer Experience research · June 2026
Managed · SDK readiness for AI
SDKs generate incorrect types occasionally
You should refine the schema layer to ensure accurate formats and structures in AI-generated code.
0
fabricated API constructs when a coding assistant was grounded in an AI-ready spec. Ambiguity in the spec is what triggers hallucinated integration code
APIMatic Context Plugins research · 6 APIs · 3 models · June 2026
Runtime Readiness
Agents make the calls
69 / 100
Elevated risk · MCP readiness
Autonomous agents cannot execute API calls
The absence of usable server URLs and inadequate operation descriptions prevent agents from safely executing payments through the Rosetta API.
65%
reduction in token consumption when agent tools are grounded in authoritative API context. Bloated or confusable tools consume up to 3.3× more.
APIMatic Context Plugins research · Series A · June 2026
The evidence numbers come from our controlled research: 6 experiments across 3 models, 6 commercial APIs, and 3 languages. We derive each card's risk status from this API's pillar scores. Full methodology at apimatic.io.
Contents