Skip to main content
Glama

Make a choice

choose

Moves a Plot Speaks choose-your-path story on by the player's choice and returns what happens next: the scene to narrate and the choices that follow, or the ending. With no choice it returns where the play is now and the path so far (for resuming). With go_back it returns to the last choice so the player can choose again. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

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": {
      "slug": "<slug>",
      "play_id": "<play_id>"
    },
    "name": "choose"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesThe story slug
choiceNoThe player's answer: the choice's number, or their words for it
go_backNoTrue when the player wants to go back to their last choice and choose again (after an ending, or any time they ask)
play_idYesThe play id from start_story

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the description only needs to add context, and it does: it discloses that the story state moves forward (so repeated calls will not be idempotent) and that go_back rewinds to the last choice. It also adds a conversational constraint that the tool must never be narrated aloud, which is real behavioral context absent from annotations. It does not say whether going back discards already-visited scenes or what happens on an unknown choice.

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?

Core behavior is front-loaded in the first sentence, with the resume and go_back variants following in a logical order. The closing instruction is somewhat padded, listing four near-synonymous phrases to avoid ("let me check", "let me check on that", "one moment", "hang on"), which could be one clause.

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?

There is no output schema, and the description carries that burden well by describing the return payload (next scene plus its choices, or the ending) and the resume shape (current position plus path so far). For a stateful, non-idempotent tool the main remaining gap is error behavior and the exact effect of rewinding.

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 goes further by tying parameters to modes: absence of choice means resume, presence of go_back means rewind-and-rechoose, and choice accepts the option number or the player's own words. slug and play_id are left to the schema, which is fine given their descriptions.

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?

States a specific verb and resource: it advances a Plot Speaks choose-your-path story by the player's choice and returns the next scene, following choices, or the ending. The mention that play_id comes from start_story orients it in the workflow. It stops short of naming a sibling like pick_for_me as the alternative for an undecided player, so differentiation is implied rather than explicit.

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?

Three distinct invocation modes are spelled out: supply a choice to advance, omit the choice to get current position and path for resuming, use go_back to return to the last choice after an ending or when asked. That is strong when-to-use coverage. It does not say when to prefer another tool, such as delegating the choice to pick_for_me, and gives no guidance on invalid or unrecognized choices.

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