Jev Harness (Apixly)

Official

by apixly-ai

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Jev Harness: execute the registered task

run_task

Destructive

Executes a caller-registered task end to end to inspect a synthetic workspace and save source evidence, returning terminal status, artifact receipt, bounded quotes, and model usage.

Instructions

Jev Harness executes the caller's registered task definition end to end for this goal: "Inspect the caller-owned synthetic workspace and save source evidence". The Jev agent loop selects registered tools and fresh argument references from observations, then runs the same independent completion check as direct operation. All inputs and source permissions are already bound by the caller; this call does not need per-step references. One client call returns terminal status, artifact receipt, bounded source quotes when the task defines an evidence report, and actual or unknown model usage. Limits: at most 20 tool effects and 120 seconds, checked cooperatively; callback I/O is bounded by the task. Only available before any operate call. Partial/review/uncertain outcomes are retained, and effects are not automatically retried.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`steps`	Yes
`report`	No	Up to four original quoted records; has_more points to subsequent read_report pages.
`status`	Yes	Terminal state; completion requires the independent check.
`artifact`	No	Caller artifact location, record count and match/digest receipt when defined.
`complete`	Yes
`telemetry`	Yes	Actual/unknown Jev model usage, requests and operation timing; caller model cost is separate.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds substantial behavioral context beyond the annotations: it discloses a 20-effect/120-second cooperative limit, retained partial/review/uncertain outcomes, no automatic retry of effects, and a single-call terminal response. With annotations already carrying destructive/open-world/idempotency hints, this is strong disclosure, though it does not explicitly characterize the destructive nature of task effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the execution purpose, followed by operational details and constraints. It is dense and mostly earns its length for a complex harness, but remains longer than necessary in places, such as repeating return-shape details already covered by the output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex end-to-end task runner with an output schema already present, the description covers purpose, binding assumptions, execution limits, response behavior, retention of partial outcomes, and temporal availability. No critical invocation context appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so the baseline is 4. The description reinforces that all inputs and permissions are caller-bound and that no per-step references are required, which is useful context even though there is no parameter schema to explain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it executes the caller's registered task definition end to end. It does not explicitly differentiate this tool from siblings like operate, observe, arguments, or read_report, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear usage constraint: the tool is only available before any operate call. It also explains that inputs and source permissions are already bound and no per-step references are needed. It does not, however, explicitly compare when to use run_task versus observe or read_report.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server