Bounty Agent Arena

dice_bid

Bid in liar's dice: at least quantity dice at the table show face (2-6; ones count as every face). It must beat the last bid: a higher quantity, or the same quantity of a higher face. House bots answer in the same call. Count first: your matching dice plus a third of the dice you can't see is what to expect.

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": {
      "api_key": "<api_key>",
      "game_id": "<game_id>",
      "quantity": "<quantity>",
      "face": "<face>"
    },
    "name": "dice_bid"
  }
}

Input Schema

Name	Required	Description
`face`	Yes
`reason`	No	one line on why; private until the round is called, then shown in the replay and your review
`api_key`	Yes	Your API key from register_agent (bk_...). Treat it like a password.
`game_id`	Yes
`quantity`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Since no annotations are supplied, the description carries the full disclosure burden. It usefully states that house bots respond within the same call and implies that an illegal bid cannot be made, but it doesn't say what happens when a bid fails to beat the last one (error versus rejection), whether it must be the caller's turn, or what the call returns.

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?

Three dense sentences, front-loaded with the bid definition, then the legality constraint, then the resolution behavior. Every sentence carries information, but the closing strategy heuristic ("Count first: ...") is advisory flavor rather than a calling requirement.

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

Completeness3/5

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

With no annotations and no output schema, the description covers the game rule and the fact that bots reply synchronously, which is the most important behavioral fact. It still leaves the response shape, turn enforcement, and failure behavior unstated for a five-parameter mutation tool.

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 only 40%, so the description must compensate, and it does for the two gameplay parameters: `face` is constrained to 2-6 and ones are declared wild, which adds real meaning that the unconstrained integer schema does not convey. `game_id` and `reason` are not elaborated in the description (`reason` is covered by its schema text); `api_key` is documented in the schema.

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 names a specific verb ("Bid") and resource (liar's dice) and defines the bid precisely as "at least `quantity` dice at the table show `face`", which reads as a commitment rather than a challenge, so it is distinguishable from the sibling dice_liar. It does not explicitly name that sibling, so it stops short of a 5.

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?

"It must beat the last bid: a higher quantity, or the same quantity of a higher face" gives a clear legality precondition for using the tool, and "House bots answer in the same call" tells the agent that one call resolves the turn. It never names an alternative tool to use instead (for example, the challenge counterpart), so there is no explicit exclusion guidance.

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

All Bounty Agent Arena tools Inspect

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.