Skip to main content
Glama
TechyAditya

jev-browser-sidekick-mcp

by TechyAditya
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

use_jev_raw

Ask Jev one or more typed decision questions in one call without a browser and get a probability for each option plus confidence, so close calls read as close and clear calls as clear.

Instructions

Ask Jev one typed question, or several. No browser.

Use whenever a decision has more than one defensible answer and you are about to pick on instinct. Jev returns a probability for every option plus a confidence, so a close call reads close and a clear one reads clear. Anything you would settle by coin flip and call judgment belongs here.

Worth handing over: which fix to do first, which name or design to ship when each has a real trade-off, whether this text meets a bar you can write down, which of two error messages a stranger reads faster, whether a step is risky enough to stop and ask the user, how to rank candidates, which reading of an ambiguous request the user meant.

Ask every question in one call. They share the state, they answer in parallel, and each extra question costs its own tokens and almost no extra time. Three questions over a page of state run about a tenth of a cent.

The answer gives the chosen option, the probability of every option, a confidence, and the tokens the API counted. Question shapes and criteria rules: jev://raw-decisions

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoPin a Jev version. Default is the configured model.
stateYesWhat every question is about. Plain text, or JSON whose fields the instructions name in backticks.
questionsYesQuestions keyed by an id you pick. Answers come back under the same ids. Ask them all in one call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.1
    • changedInput schema / properties / questions / additionalProperties / properties / criteria / description
      Previous value: -"Options for choice (max 255), keyed by your own names. Ordered levels for score (max 10), as an array, lowest first. For noul, the two keys true and false, each describing what that answer means."New value: +"Options for choice (max 255), keyed by your own names. Ordered levels for score (max 10), as an array, lowest first. For noul, the keys true and false, each describing what that answer means."
    • changedInput schema / properties / questions / additionalProperties / properties / instructions / description
      Previous value: -"The whole question, written out. The question id is not sent to the model."New value: +"The whole question, written out. The id is not sent to the model."
  2. First observedv0.1.2

TDQS

A4/5.0
Behavior4/5

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

No annotations, so the description carries the full burden, and it delivers real behavioral context: answers return a chosen option, per-option probabilities, a confidence, and API-counted tokens; questions share state, run in parallel, and cost roughly a tenth of a cent for three questions. Auth/prerequisites and failure modes are not covered.

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?

Purpose and the core output contract are front-loaded, and the cost/parallelism note is useful. The eight-item "worth handing over" list is longer than needed and pushes length up, but each block still carries usable information.

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 tool with nested question objects, no output schema, and no annotations, the description covers what the response contains and points to jev://raw-decisions for question shapes and criteria rules. It leaves undefined what Jev itself is and any rate-limit or error behavior, but is otherwise sufficient to call correctly.

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?

Schema coverage is 100% so the baseline is 3, but the description adds semantics the schema cannot: every question should be asked in one call, they share state, and batching adds tokens but almost no latency. That meaningfully shapes how the parameters are populated beyond their field descriptions.

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 opening sentence states a specific verb and resource ("Ask Jev one typed question, or several") and rules out a browser variant, and the second paragraph makes concrete what Jev actually does: returns probabilities per option plus a confidence. It is clear what the tool is for, though the only listed sibling (run_action) is never distinguished.

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 trigger ("whenever a decision has more than one defensible answer and you are about to pick on instinct") plus a concrete list of qualifying scenarios and an implicit exclusion (anything settled mechanically by coin flip is only worth it because it's judgment). No alternative tool is named, so it stops short of full when-not/alternative routing.

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