Recommends model tier, reasoning effort, and context tier from a task description and context size, letting coding agents route work offline without manual grouping.
Zero-config offline autopilot selector that recommends model tier, reasoning_effort (low/medium/high), and context tier without manual grouping.
| Name | Required | Description | Default |
|---|---|---|---|
| context_chars | No | Approximate context character count. | |
| task_description | Yes | Task description or prompt. |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the whole behavioral burden. It does disclose two useful traits — the selector runs offline and needs no configuration or manual grouping — which tells the agent this is a cheap, self-contained heuristic rather than a network-backed service. It says nothing about determinism, whether the recommendation is advisory or binding, or the shape of the result, which matters since there is no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with the capability stated immediately and no filler. Minor redundancy: "zero-config" and "without manual grouping" express nearly the same idea.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is low-complexity with two well-documented params, and the description names the three recommendation axes. However, with no output schema, it should describe the return value's structure (a single tier triple? a per-axis object?) and whether confidence or rationale is included. That gap keeps it merely adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so context_chars and task_description are already documented in the schema. The description hints at the reasoning_effort enum it produces (low/medium/high) but adds no guidance on how task_description influences the recommendation or how context_chars is used. Baseline 3 applies when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description pairs a specific verb ("recommends") with three concrete outputs: model tier, reasoning_effort, and context tier. That is far more informative than the opaque name jev_autopilot. It stops short of distinguishing itself from the sibling jev_route, leaving the agent to guess which is the general router and which is the zero-config autopilot.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Zero-config" and "without manual grouping" imply the use case: call this when you don't already know the tiering and don't want to specify grouping yourself. No explicit when-not conditions, prerequisites, or named alternatives (e.g., jev_route) are given, so routing between siblings is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.