Skip to main content
Glama
Sign In

iDos Games

by com.idosgames
OverviewDiscussionsAdmin

Surprise Jev tuning

tuning_surprise

"Surprise me": a bold random pick for every unpinned knob, weighted by the decision model's saved answers (free, no decision-model call). Saves nothing: returns the plan to show or apply.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "title_id": "<title_id>"
    },
    "name": "tuning_surprise"
  }
}

Input Schema

NameRequiredDescriptionDefault
knobsNoOptional: limit to these knob ids.
title_idYesTitleID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

"Saves nothing: returns the plan to show or apply" is the key disclosure — no persisted state, output is advisory only — which annotations (readOnlyHint=false, destructiveHint=false) do not convey. "Weighted by the decision model's saved answers (free, no decision-model call)" adds cost and data-source behavior. There is mild tension with readOnlyHint=false since the text describes a non-persisting operation, though this reads as a conservative annotation default rather than a direct contradiction.

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

Conciseness5/5

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

Two short clauses, zero filler. The random-pick purpose comes first, then the cost note, then the no-side-effect/return contract — the most decision-relevant facts are front-loaded.

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?

With no output schema, the description correctly states what comes back (a plan, not an applied change) and how it is consumed (show or apply), which is exactly what an agent needs. It stops short of placing the tool in the full tuning workflow next to preview/reroll/undo.

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 coverage is 100%, so both parameters are documented and the baseline is 3. The description adds one real semantic beyond the schema: knobs outside the `knobs` list — specifically pinned ones — are excluded from the random pick, which links this tool's behavior to tuning_pin.

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 uses a concrete verb+resource combo ("bold random pick for every unpinned knob") plus a memorable alias ("Surprise me"), so the agent knows exactly what the tool produces. It does not name the closest siblings (tuning_reroll, tuning_preview, tuning_apply), so differentiation is left implicit.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: "returns the plan to show or apply" signals the follow-up step is tuning_apply, and "free, no decision-model call" tells the agent there is no cost to trying it. It never says when to choose this over tuning_reroll or tuning_preview, nor what happens with pinned knobs beyond excluding them.

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

All iDos Games toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources