Skip to main content
Glama
Sign In

tokyo-futuro

by io.github.TokyoFuturo
OverviewDiscussionsAdmin

prepare_night_run_enter

Night Run: prepare (unsigned) entry into an open race as the leader. Pass a vehicleId you hold (only a Sentinel or a Courier can race; a Hauler, helicopter or jet is refused; pays the entry stake into the pot, can win it) or 0 for a free city loaner (no stake, can never win the pot). Squad 1 to 4 wallets. Roles: 1 Driver (required), 2 Hacker, 3 Muscle, 4 Inside Agent. In the Night Run roles only split the prize (Driver 40, Hacker 25, Muscle 20, Inside Agent 15); they add no odds.

Input Schema

NameRequiredDescriptionDefault
houseNoOnly for the team's own HOUSE wallets (they hold the house role and must use the house door; everyone else leaves this out). A house entry needs a vehicle.
rolesNoOne role number per member, same order. Role ids differ per game (see this tool's description).
raceIdYesFrom race_list.
walletYesYour own 0x wallet address. Nothing is sent from it; it is used to read your balance and allowance and to simulate.
membersNoCrew wallets, YOU first (each other member must have called prepare_approve_leader for you). Omit to go alone where the game allows. The size limit is per game: night_run 1-4, convoy 1-5, ledger 2-5, vehicle_heist 2-5, raid 2-4.
vehicleIdNoA vehicle token you hold, or 0 for a loaner.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / house
      Added value: +{
+  "description": "Only for the team's own HOUSE wallets (they hold the house role and must use the house door; everyone else leaves this out). A house entry needs a vehicle.",
+  "type": "boolean"
+}
    • changedInput schema / properties / members / description
      Previous value: -"Crew wallets, YOU first (each other member must have called prepare_approve_leader for you). Omit to go alone where the game allows. The size limit is per game: night_run 1-4, convoy 1-5, ledger 2-5, vehicle_heist 3-5, raid 2-4."New value: +"Crew wallets, YOU first (each other member must have called prepare_approve_leader for you). Omit to go alone where the game allows. The size limit is per game: night_run 1-4, convoy 1-5, ledger 2-5, vehicle_heist 2-5, raid 2-4."
  2. Added

TDQS

A4.5/5.0
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 does it well: the entry is unsigned, the stake is paid into the pot and is winnable, a loaner pays no stake but can never win, and roles only split the prize (Driver 40/25/20/15) with no odds impact. These are material consequences an agent cannot infer from the schema.

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?

Front-loaded with the action and eligibility, then the stake/loaner tradeoff, then squad and roles. It is dense with nested parentheticals, but every sentence carries decision-relevant information rather than restating the name.

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 6-param mutation tool with no annotations and no output schema, it covers eligibility, economics, squad composition and role semantics thoroughly. The one gap is what follows preparation (signing/submission of the unsigned entry), which the agent must infer from the 'prepare' naming convention.

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 real meaning: vehicleId accepts a held token or 0 for a free loaner, and roles are numbered 1-4 with an explicit mapping and prize-split percentages, which the schema only gestures at ('see this tool's description'). The house parameter is left entirely to 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 ('prepare (unsigned) entry into an open race') plus the actor position ('as the leader'), which separates it from prepare_night_run_back and prepare_night_run_claim among the siblings. An agent can tell what this produces without reading the schema.

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 clear entry conditions: which vehicles qualify (Sentinel/Courier only; Hauler, helicopter or jet refused), the stake-vs-loaner fork, and squad sizes 1-4. It never names a sibling alternative (e.g. backing another leader via prepare_night_run_back), so routing guidance is implied by 'as the leader' rather than explicit.

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

All tokyo-futuro 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