Skip to main content
Glama

Get a scene cue

get_cue

Returns one scene cue from a Plot Speaks mystery or adventure script, as text: a READ ALOUD part (the scene as spoken narration) and, where the cue has them, NARRATOR NOTES that are not meant to be read aloud because they would spoil the scene; cue S1 also lists the follow-up cues to listen for. With a play id it records the scene reached as an anonymous play event, which the play's watch page shows as a timeline. An unknown slug returns an error naming the available stories; a cue id the story lacks returns an error saying so (or that the story has no cues). 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>",
      "cue": "<cue>"
    },
    "name": "get_cue"
  }
}

Input Schema

NameRequiredDescriptionDefault
cueYesThe cue id as written in the story's script: S, a number and an optional letter; the S and case may be omitted. E.g. S1, S3b or 3b
slugYesThe story slug or title, e.g. example-dinner-party
play_idNoThe play id start_story returned, e.g. 3f2b8c1e-9d4a-4e7b-a1c2-5b6d7e8f9a0b; when given, the cue is logged against that play

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / cue / description
      Previous value: -"The cue id, e.g. S1 or S3b"New value: +"The cue id as written in the story's script: S, a number and an optional letter; the S and case may be omitted. E.g. S1, S3b or 3b"
    • changedInput schema / properties / play_id / description
      Previous value: -"The play id from start_story"New value: +"The play id start_story returned, e.g. 3f2b8c1e-9d4a-4e7b-a1c2-5b6d7e8f9a0b; when given, the cue is logged against that play"
    • changedInput schema / properties / slug / description
      Previous value: -"The story slug"New value: +"The story slug or title, e.g. example-dinner-party"
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and idempotentHint=false; the description explains exactly what the non-read-only side effect is — an anonymous play event that surfaces as a timeline on the play's watch page. It also discloses that NARRATOR NOTES are spoiler material not to be read aloud and predicts both error messages, which the annotations cannot convey.

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 return value, then the side effect, then error behavior — a sensible order. It is dense and run-on in places, and the closing silence directive spends several tokens enumerating near-synonymous phrasings ('let me check', 'one moment', 'hang on') that could be compressed.

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 3-parameter tool with no output schema, the description covers the return shape, the write side effect, the spoiler constraint, and both error cases — everything an agent needs to call it and interpret the result correctly.

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 baseline is 3, but the description adds real meaning: it explains that cue S1 enumerates follow-up cues to listen for, and that play_id has a downstream effect (timeline entry on the play's watch page). The cue and slug parameters are otherwise left 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 precise verb and resource ('Returns one scene cue from a Plot Speaks mystery or adventure script') and goes on to define the resource's internal shape (READ ALOUD narration vs. spoiler-bearing NARRATOR NOTES). That level of specificity makes it unmistakable against siblings like list_stories or start_story without needing to name them.

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 clarifies the main usage fork: pass play_id to record the scene reached, omit it for a plain read. It also sets expectations for two failure paths (unknown slug names available stories; missing cue id says so). It stops short of explicitly routing to alternatives (e.g. how to discover a slug or get a play id), leaving that inference to the agent.

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