jevqueue
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jevqueue_decideA | Ask the decision layer whether a pending step should run, before running it. Returns the verdict, the action, the confidence, the risk triage and the completion probability. Use it before a destructive or irreversible step, and before continuing on work that may already be finished. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of overlap or misselection between tools. Its stated purpose—querying a decision layer before a risky or redundant step—is clearly bounded and not duplicated elsewhere in the set.
The single name `jevqueue_decide` uses a predictable server-prefix + verb pattern that reads clearly. With only one tool there is no mixed convention, though also no broader pattern to confirm consistency across a set.
A one-tool surface is extremely thin for a server presented as a decision layer; the rubric treats a single tool as too few for the apparent scope. All decision functionality is crammed into one opaque call with no separate operations for outcome reporting, pending-step inspection, or configuration.
If the server is purely a read-only verdict oracle, one tool can cover its core purpose. However, there are notable gaps: no way to report whether a decision was correct, no listing of pending steps, and no batch or parameterized variants, making the lifecycle only partially closed.