AI Readiness AuditRef. APM-9B4D2111 · Confidential
nevisAuth REST API
An independent assessment of whether the nevisAuth REST API specification is ready for AI-assisted integration and autonomous agents, prepared for Nevis.
76/100
Needs work
Gaps for AI-assisted builds.
Broken for autonomous agents.
Broken for autonomous agents.
Reach AI-ready by Phase 1; resolve all findings → 100 · AI-ready
F
D
C
B
A
76
055708085100
F · Not readyD · Significant gapsC · Needs workB · Mostly readyA · AI-ready
0
Critical blockers : no findings stop an operation group outright
403
Total instances: 0 critical, 52 high, 162 medium, 189 low
33
Rule groups across 4 pillars: 0 critical, 52 high sev. instances
Executive summary
Your nevisAuth REST API scores 76 out of 100, reflecting areas that need work. Standards compliance stands strong at 89.1, while documentation readiness for AI reveals significant gaps at 67.7. SDK readiness for AI scores 76.4, and MCP readiness drops to 64.1, also showing significant gaps. The most urgent action is to address the documentation readiness to improve AI integration.
Readiness by pillar
Needs work
76 / 100
FoundationThe spec itself
89/100
Standards Compliance
OpenAPI validity, structural correctness, specification conformance, and import linting: can machines trust your spec?
89AI-ready
Build Time ReadinessAI writes the code
72/100
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
68Significant gaps
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
76Needs work
Runtime ReadinessAgents make the calls
64/100
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
64Significant gaps
Score projection · what fixing each phase unlocks
Todaycurrent score
Phase 1fix highs
Phase 2+ fix mediums & lows
About this report. We evaluated the nevisAuth REST API 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
89 / 100
Managed · Standards compliance
Address schema issues in media types
You maintain a strong compliance score, but missing schemas and circular references in the nevisAuth API can disrupt toolchains and SDK generation.
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
72 / 100
Elevated risk · Documentation readiness for AI
AI readers misinterpret API due to gaps
The nevisAuth REST API lacks essential parameter descriptions, leading to incorrect assumptions in builds.
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
Elevated risk · SDK readiness for AI
SDKs return incorrect types and formats
You should clarify the success response schema to ensure accurate integration with the identity API.
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
64 / 100
Elevated risk · MCP readiness
Autonomous Agents Fail to Execute API
Agents cannot select or call the nevisAuth API due to missing server URLs and inadequate operation descriptions, risking identity management.
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