Skip to main content
Glama
Sign In

Tavern

by io.github.jakehandy
OverviewDiscussionsAdmin

Set up a battle

create_battle

Start a battle's roster. Nothing happens until it is started. GM only. Returns: The battle.

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": {
      "campaign": "<campaign>"
    },
    "name": "create_battle"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoWhat to call it.
campaignYesThe campaign, by its slug (what its link says) or its id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive behavior, but the description adds two things they cannot express: the GM-only authorization requirement and the fact that creation is inert until a separate start call. That is real behavioral context; it only falls short of 5 because it never says what the returned battle contains or what state it begins in.

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 short, front-loaded sentences with no padding, and the inertness caveat sits right after the purpose statement where it matters. The opening phrase "Start a battle's roster" is the weakest wording and creates avoidable ambiguity with start_battle.

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?

For a two-parameter creation tool with no output schema, the description covers auth, inert-until-started semantics, and return value. It still leaves the core object underspecified — whether a created battle is a roster container, what an agent should do next, and how it differs concretely from start_battle remain unstated.

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 description coverage is 100%, so both the optional name and the campaign slug/id parameter are fully documented in the schema itself. The description adds no parameter-level meaning, which is acceptable at full coverage but earns only the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Start a battle's roster" gestures at creating a battle container, but the verb is ambiguous against the sibling start_battle — an agent could read this as beginning combat rather than creating an inactive battle. The clarifying line "Nothing happens until it is started" partially resolves this, but the sibling is never named, so the distinction stays 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?

"Nothing happens until it is started" implies a two-step flow and thus when to pick this over start_battle, and "GM only" states a prerequisite. However, no alternative tool is named and there is no explicit "use this when / not when" framing, leaving the routing to inference.

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

All Tavern 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