The measure of
agent-readiness

v0.9 March 2026 71 criteria 12 modules open methodology

Developer tools have a new class of customer. Already today, AI coding agents are choosing and using tools at a higher rate than humans.

Is your tool ready for them?

The Standard at a glance

The Zaira Standard defines what "Agent Ready" means: 71 criteria across all domains of a tool's function, based on broad industry research, delivered in an open methodology.

What's measured

Base Standard applies to all tools. Additional modules activate based on tool complexity.

Base Standard 15 criteria
Complexity modules (5) 36 criteria
Domain modules (6) 20 criteria
Total 71 criteria

How it's scored

Scoring gradients are built to reflect realistic use cases and how agents work today.

0
Not present
1
Basic
2
Solid
3
Exemplary

Where you stand

The Zaira Score is the weighted percentage across all applicable modules.

Agent Ready ≥60%
All MUST criteria pass
Agent Native ≥80%
All MUSTs ≥2, zero gaps

The best tools are independently evaluated. See what it takes to get Zaira Certified.

One standard, right-sized for every tool

"Developer tools" is a broad category where different tools have different needs. Agent-readiness looks very different for a simple utility library vs. a payment processing API. The Standard is intentionally modular: a base evaluation applies to every tool, with additional complexity modules activating based on what your tool actually does. You're only measured on what's relevant.

15
criteria

Base Standard

Applies to every tool, always. The foundation everything else builds on.

Documentation quality, machine-readable formats, error handling, versioning, security posture, maintenance signals, licensing.

Complexity modules activate based on what the tool does
Module # When Coverage
PIProgrammatic Interface16Tool exposes an API, SDK, or MCP serverSDK quality, API design, type safety, error contracts
NSNetwork Service8Tool is a hosted or remote serviceUptime, error responses, rate limiting, latency
WOWrite Operations4Tool creates, modifies, or deletes dataIdempotency, rollback, conflict handling
AUAuthentication4Tool requires credentials or tokensKey management, token flows, non-interactive auth
CLICLI4Tool has a command-line interfaceExit codes, machine-readable output, scriptability
Domain modules criteria specific to a tool's domain
Module # When Coverage
PMPayments4Tool processes paymentsTest mode parity, webhook verification, PCI scope
CMCommunications3Tool sends messages or notificationsDelivery status, templates, channel abstraction
DBDatabases4Tool stores or queries dataMigrations, connection pooling, schema introspection
HIHosting3Tool deploys or hosts applicationsDeploy automation, environment parity, scaling
APAuth Providers3Tool manages user identityNon-interactive flows, MFA, session management
FLFrameworks3Tool scaffolds or structures applicationsScaffolding, conventions, plugin architecture

How modules activate

Your tool's characteristics determine which modules apply.

Complex tool: payment API

Has an SDK, runs as a network service, handles write operations, requires authentication, operates in the payments domain.

Base (15) + PI (16) + NS (8) + WO (4) + AU (4) + PM (4) = 51 criteria

Simple tool: open-source library

No API, no network calls, no auth. A library you install and call. Only the Base Standard applies.

Base (15) = 15 criteria

Want to know what this looks like
in practice?

The Best Practices Guide walks through every criterion with concrete and realistic implementation patterns with real examples.

Best Practices Guide →

Built on evidence, not opinion

The Zaira Standard wasn't designed in a vacuum. Every criterion traces back to published research, real-world incident data, or empirical measurement of how agents actually interact with developer tools. The findings shaped what we measure and why.

40+
academic research sources
1,400+
MCP servers analyzed
400+
tools vulnerability-tested
844K+
llms.txt files investigated

Examples from the research

Each finding below directly shaped a criterion in the Standard.

Finding

43% of MCP servers have command injection vulnerabilities. 84% attack success rate via prompt injection against major coding agents.

standard response

Safety criteria are MUST gates. A tool that scores perfectly on documentation but fails safety cannot earn any designation. Security is non-negotiable.

Finding

Structured error messages improve agent recovery by 4.75x. 97.1% of MCP tool descriptions have quality defects. Adding examples boosts success from 11% to 76%.

standard response

Error handling and tool description quality are weighted as Critical (2x) in scoring. These aren't nice-to-haves. The data shows they're the difference between an agent that recovers and one that fails.

Finding

Good documentation improves agent accuracy by 91%. But more documentation is not better. Accuracy degrades 30%+ when relevant information sits in the middle of large context.

standard response

Documentation criteria evaluate structure and extractability, not volume. The Standard rewards answer-first layouts, semantic sections, and machine-readable formats over comprehensive reference dumps.

Additional metrics and research findings can be found throughout the Standard and Best Practices Guide.

Open and stable

The Zaira Standard is public and stable. Revisions are made only when durable shifts in agent-tool interaction warrant them, not in response to short-term trends. Certified tools receive at least 30 days advance notice before any version change takes effect, giving vendors time to adapt ahead of the transition.

The first version is purposefully v0.9 to signify the expected tuning based on pilot evaluation feedback before v1.0 is published.

current_version
v0.9 March 2026
Read the Standard v0.9