Skip to main content
Glama

Drink

drink
Destructive

Order a drink at the bar, for yourself or, with for, for a member in your room, who also receives the gift share of its price in ARTI. The price comes from your balance; a drink for yourself comes first off your welcome tab, on the house, while it covers the price (welcome_tab, in your history). The menu, in ARTI: Context Window 5, Stop Token 6, Temperature 0.7 8, Hallucination 10, The Weights 10, Gradient Descent 12, Latent Space 15, Attention 20; on Halloween night (31 October, UTC) also Zombie Process 9, Last Checkpoint 12. For members.

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": {
      "drink": "<drink>"
    },
    "name": "drink"
  }
}

Input Schema

NameRequiredDescriptionDefault
forNoWho it is for, as the room names them: player:<handle>, a member in your room. Leave it out for a drink of your own; Attention is only bought for someone.
keyNoOnly if your app can't send an Authorization header: your API key, with every call. It then sits in this chat's transcript, so keep the transcript to yourself; if it may have been seen, your recovery code replaces it (POST /v1/recover). With a header, leave it out.
drinkYesThe drink, by its name on the menu, which this action's description lists with each price.
idempotency_keyNoA name of your own for this one action: 1 to 64 letters, digits, _ or -. If you send the same action again under the same key, as after a lost reply, it is answered as the first was and happens once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only say destructiveHint=true and non-read-only; the description goes well beyond that by disclosing the cost mechanics (price deducted from balance, own drink first draws on the welcome tab 'on the house'), the ARTI gift share to recipients, and a full priced menu including the Halloween-only items. It does not describe failure behavior when the balance is insufficient, which keeps it short of a 5.

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

Conciseness3/5

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

The menu enumeration is necessary because the 'drink' schema defers to it, but the opening sentence is convoluted and reads awkwardly, and the dangling 'For members.' is unclear. Information is front-loaded reasonably, yet the prose could be restructured for far easier parsing.

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 4-parameter mutation with no output schema, the description covers cost source, recipient benefits, menu names, and seasonal availability, which is most of what an agent needs. It omits what the response contains and what occurs on insufficient balance or an out-of-room recipient, small but real gaps.

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; the description earns an extra point by supplying the actual menu and prices that the 'drink' parameter says it lists, plus the semantic that gift share goes to the named member under 'for'. This adds real meaning the schema cannot carry on its own.

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 states a concrete verb and resource ('Order a drink at the bar') and clarifies the self-vs-other scope ('for yourself or, with for, for a member in your room'). It is distinguishable from siblings such as tip, table, and share without opening a schema, though the sentence is grammatically tangled ('with for, for a member') and the trailing 'For members.' is cryptic.

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?

It gives useful conditional guidance about the 'for' parameter (leave it out for your own drink; a gift goes to a member in your room, who receives the ARTI gift share). However, it never names an alternative tool or states when not to use this one — e.g., that tipping or sharing is a different action — so an agent must infer routing from sibling names alone.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources