Skip to main content
Glama

Read a scene's contents

dos2_scene
Read-onlyIdempotent

Reads a saved GM scene from campaign files: placed characters, encounters, item count and sticky notes. Use it to inspect prepared scenes; for a running game, use the live tools.

Instructions

Reads what the Game Master has placed in one scene, from the campaign files (LevelCache): characters with name, root template, position, vitality, experience, alignment and encounter; encounters with their members; the item count; the scene's sticky notes.

Read-only, and it shows the saved state, not a running game: for the live level use dos2_live_characters. Placed
characters cannot be edited through files; change them in the game or with the dos2_live_* tools. Fails with an
error if the scene has never been loaded in the game (it has no LevelCache file yet).

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>",
      "scene": "<scene>"
    },
    "name": "dos2_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of characters to list (default 200).
sceneYesScene name or scene ID, as listed by dos2_campaign.
campaignYesThe campaign to work on: its name, its folder name, its UUID, or a unique part of any of them. dos2_status lists the campaigns.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.1
    • addedInput schema / properties / campaign / description
      Added value: +"The campaign to work on: its name, its folder name, its UUID, or a unique part of any of them. dos2_status lists the campaigns."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of characters to list (default 200)."
    • addedInput schema / properties / scene / description
      Added value: +"Scene name or scene ID, as listed by dos2_campaign."
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, but the description adds real value beyond them: it clarifies this is the saved on-disk state rather than a running game, and that it fails when no LevelCache file exists. It also states placed characters cannot be edited through files. Only the return-shape detail is thin, which is excusable given the field list is already provided.

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 resource and its returned fields, then the live-vs-saved distinction and the failure mode. The field enumeration is long but pays for itself because no output schema exists; a little tightening is possible but nothing is filler.

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 read tool with no output schema, the description covers return contents, data source, freshness semantics, editability limits and the error condition. An agent can decide and call correctly without further information.

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 campaign, scene (name/ID as listed by dos2_campaign) and limit. The description adds nothing parameter-specific beyond that baseline; the default-200 limit and its truncation behavior are never discussed.

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 specific verb (reads) and resource (a scene's placed contents), and immediately enumerates what is returned: characters with their fields, encounters, item count, sticky notes. It is clearly distinguishable from dos2_live_characters, which it names explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit alternative for live data ('for the live level use dos2_live_characters') and an explicit constraint on what to do instead when editing is needed (change them in the game or use dos2_live_* tools). Both the when and the when-not are covered.

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