Skip to main content
Glama
rust-works

omni-dev

by rust-works
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

jev_route

Route GitHub issues to model classes for design, implementation, and review, returning model picks, probabilities, and dependencies as JSON or YAML.

Instructions

Route GitHub issues to model classes for design, implementation and review. Mirrors ai jev route; returns models, usage, probabilities, close calls, dependencies and cache metadata as JSON/YAML. Supply issues OR all_open. Draft comments are local previews and never posted. Requires gh authentication and configured Jev credentials. Closed issues are refused by default. Partial issue failures retain the report with isError=true; authentication failures abort.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repoNoRepository directory for bare references/all_open; defaults to server cwd.
issuesNoIssue references: N, #N, owner/repo#N or GitHub issue URL. Exclusive with all_open.
outputNoReport format: json (default) or yaml.
laddersNoNamed ladders; defaults to `["anthropic"]`. Built-ins: anthropic, openai, gemini.
refreshNoBypass the shared GitHub issue cache.
all_openNoRoute every open issue in the repository instead of supplying issues.
jev_modelNoJev model override, independent of the AI backend model.
close_callNoConfidence below which an answer is a close call; default 0.3.
allow_closedNoAllow closed issues (their completed work can bias routing).
draft_commentNoLocal UTF-8 draft comment paths, one issue only; never posted to GitHub.
effort_adviceNoAsk for per-model effort recommendations (additional Jev questions).
ignore_closedNoSkip closed issues; exclusive with allow_closed.
max_input_charsNoInput character cap; default 60000. Longer input has a truncation marker.
close_call_marginNoTop-two probability gap below which a stage is a close call; default 0.2.
ladder_definitionNoCustom ladder definitions loaded from local YAML files.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.45.0

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and discharges it well: it states auth prerequisites (gh authentication plus Jev credentials), a side-effect safeguard (draft comments are local previews and never posted), and error semantics (partial failures retain the report with isError=true, auth failures abort, closed issues refused by default).

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?

Five sentences, each carrying distinct information, with purpose first and operational constraints after. It is dense but nothing is filler; only slight compression would improve it.

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

Completeness4/5

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

For a 15-parameter tool with no output schema, the description names what is returned (models, usage, probabilities, close calls, dependencies, cache metadata) and covers auth, side effects, and failure modes. Adequate, though additional detail on the report shape would help.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 15 parameters. The description only restates the issues/all_open exclusivity and the default closed-issue behavior, adding little semantics beyond the schema.

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

Purpose5/5

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

States a specific verb and resource: 'Route GitHub issues to model classes for design, implementation and review.' No sibling tool performs routing, so the distinction is clear, and the sentence is front-loaded.

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?

Gives an explicit input rule ('Supply issues OR all_open') and a standing constraint ('Closed issues are refused by default'), which implies when-not usage. It stops short of naming alternative tools or workflows for the cases where routing is not wanted.

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

Deploy Server

Other Tools