Skip to main content
Glama

Start a story

start_story

Loads a Plot Speaks story or game, of any kind (mystery, choose-your-path, trivia, dice or word game, Team Trivia, campaign), by slug or title. Returns its script as text (setting, cast, scenes or board, and how it is narrated; one chapter at a time for multi-chapter stories) and a play id the play's other tools take. Records an anonymous play (story, connecting assistant, time; no conversation text), and on the account connector adds it to the player's history. An unknown slug or title returns an error naming close matches or the available stories; a chapter past the last returns an error; an unreleased chapter returns its release date. 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>"
    },
    "name": "start_story"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesThe story's slug or title, matched loosely, 2 to 80 characters, e.g. example-dinner-party or The Last Toast
teamNoFor the team-trivia story: the team as the player said it, e.g. Steelers, Pittsburgh or PIT; "Yankees vs Red Sox" gives a rivalry board. Several matches or an unsupported team return a message instead of a board
chapterNoChapter number for a multi-chapter story, e.g. 2 for the second chapter (default 1); an error if the story has fewer chapters
minutesNoFor a trivia game: minutes the player has, e.g. 25, so the game is sized to fit
play_idNoWith chapter above 1: the play id returned for chapter 1, e.g. 3f2b8c1e-9d4a-4e7b-a1c2-5b6d7e8f9a0b, so both chapters count as one play; ignored if it belongs to another story
path_codeNoFor a choose-your-path story: the three-word path code a friend received at an ending, e.g. brave-river-stone, to follow that friend's choices; codes last 30 days, an unknown one returns an error
resume_codeNoFor a campaign: the three-word code given at the end of an earlier session, e.g. amber-otter-lantern; carries on that campaign's world instead of starting one. An unknown code returns an error
versus_codeNoFor a trivia board: the three-word code a friend received at the end of their game, to play the same board and compare scores; pass slug "versus" with it, the code names the game. Codes last 30 days
new_campaignNoFor a campaign, when a signed-in player already has one: true starts a fresh campaign instead of carrying on their latest (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • changedInput schema / properties / chapter / description
      Previous value: -"For a two-chapter story: 2 to get chapter 2 (default 1)"New value: +"Chapter number for a multi-chapter story, e.g. 2 for the second chapter (default 1); an error if the story has fewer chapters"
    • changedInput schema / properties / minutes / description
      Previous value: -"For a trivia game: how long the player has (their drive), to size the game to it"New value: +"For a trivia game: minutes the player has, e.g. 25, so the game is sized to fit"
    • changedInput schema / properties / new_campaign / description
      Previous value: -"For a campaign, when the player is signed in and has one already: true to start a fresh one instead of carrying on"New value: +"For a campaign, when a signed-in player already has one: true starts a fresh campaign instead of carrying on their latest (default false)"
    • changedInput schema / properties / path_code / description
      Previous value: -"For a choose-your-path story: the three-word path code a friend got at its ending, to follow their choices"New value: +"For a choose-your-path story: the three-word path code a friend received at an ending, e.g. brave-river-stone, to follow that friend's choices; codes last 30 days, an unknown one returns an error"
    • changedInput schema / properties / play_id / description
      Previous value: -"With chapter 2: the play id from chapter 1, to keep the same play"New value: +"With chapter above 1: the play id returned for chapter 1, e.g. 3f2b8c1e-9d4a-4e7b-a1c2-5b6d7e8f9a0b, so both chapters count as one play; ignored if it belongs to another story"
    • changedInput schema / properties / resume_code / description
      Previous value: -"For a campaign: the three-word code from an earlier session, to carry on where it left off"New value: +"For a campaign: the three-word code given at the end of an earlier session, e.g. amber-otter-lantern; carries on that campaign's world instead of starting one. An unknown code returns an error"
    • changedInput schema / properties / slug / description
      Previous value: -"The story's slug or title, e.g. example-dinner-party or The Last Toast"New value: +"The story's slug or title, matched loosely, 2 to 80 characters, e.g. example-dinner-party or The Last Toast"
    • changedInput schema / properties / team / description
      Previous value: -"For Team Trivia: the team the player named, in their words (a city, a name, a nickname or an abbreviation)"New value: +"For the team-trivia story: the team as the player said it, e.g. Steelers, Pittsburgh or PIT; \"Yankees vs Red Sox\" gives a rivalry board. Several matches or an unsupported team return a message instead of a board"
    • changedInput schema / properties / versus_code / description
      Previous value: -"For a trivia board: the three-word code a friend got at the end of their game, to play the same board and compare scores (pass slug \"versus\"; the code names the game)"New value: +"For a trivia board: the three-word code a friend received at the end of their game, to play the same board and compare scores; pass slug \"versus\" with it, the code names the game. Codes last 30 days"
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), it discloses a non-obvious side effect: an anonymous play record is written (story, connecting assistant, time; explicitly no conversation text), and on the account connector it is added to history. It also documents error behavior (unknown slug returns close matches or available stories, chapter past the last errors, unreleased chapter returns its release date) and the silent-invocation requirement.

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?

It is front-loaded with purpose and return value before side effects and error cases, and most sentences carry unique information. The silent-call instruction is padded with four quoted example phrases ('let me check', 'let me check on that', 'one moment', 'hang on'), which is more repetition than needed.

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

Completeness5/5

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

For a nine-parameter, no-output-schema tool, the description covers return content (script text: setting, cast, scenes or board, narration), the play id the other tools consume, side effects and privacy, and the main failure modes. Nothing an agent needs to invoke it correctly is missing.

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 the schema already documents all nine parameters in detail. The description adds little parameter-level meaning beyond noting one-chapter-at-a-time loading and slug-or-title addressing, both of which the schema states. Baseline 3 applies when the schema does the heavy lifting.

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?

The description opens with a specific verb and resource ('Loads a Plot Speaks story or game') and enumerates the covered kinds (mystery, choose-your-path, trivia, dice/word game, Team Trivia, campaign), plus how it is addressed ('by slug or title'). It also states what comes back (script text and a play id), so an agent can distinguish it from list_stories or pick_for_me without opening 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?

It gives clear conditions for each mode of invocation — chapter for multi-chapter, path_code for following a friend's path, resume_code for continuing a campaign, versus_code for a shared trivia board, new_campaign for starting fresh — which is strong contextual guidance. It never names a sibling tool as an alternative (e.g. for discovering a slug when the error lists available stories), so it stops short of explicit routing.

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