Skip to main content
Glama
Sign In

Backlog Quest

by site.chatgpt.bright-moose-6173.backlog-quest-lab
OverviewDiscussionsAdmin

create_backlog_quest

Read-onlyIdempotent

Read-only: choose exactly one title from an ordered 2–12 game backlog and return the selected game, session length, mood, language, and a ready-to-follow time-boxed instruction. It never launches, buys, installs, modifies, or accesses a game or account. Use quick to start immediately, focus for one clear objective, chill for low-pressure play, or challenge for a difficult but reachable objective. The same seed plus the same ordered games list selects the same game; omit seed for a fresh random choice. No account, store login, or payment is required. Game titles and seed are processed in memory and are not stored; only an aggregate request event is recorded.

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the generated instruction: en for English or ru for Russian. Defaults to en.en
moodNoQuest style: quick starts immediately, focus picks one clear objective, chill avoids progress pressure, and challenge asks for a difficult but reachable objective. Defaults to focus.focus
seedNoOptional repeatability key, up to 64 characters. The same seed plus the same normalized ordered games list selects the same game; omit it for a fresh cryptographically random choice.
gamesYesOrdered list of 2–12 distinct game titles to choose from. Order matters when seed is supplied.
minutesNoLength of the play session in minutes. Defaults to 60.

Output Schema

NameRequiredDescriptionDefault
questYesThe selected game and the bounded play instruction.
privacyYesHow request data and aggregate measurement are handled.
human_urlYesBrowser version of Backlog Quest with machine-source attribution.
documentation_urlYesHuman-readable API and MCP documentation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / description
      Added value: +"Inputs for selecting one game and generating a bounded play session. Game titles and the optional seed are processed in memory and are not stored."
    • addedInput schema / properties / games / description
      Added value: +"Ordered list of 2–12 distinct game titles to choose from. Order matters when seed is supplied."
    • addedInput schema / properties / games / items / description
      Added value: +"A game title, trimmed to 1–80 characters."
    • addedInput schema / properties / lang / description
      Added value: +"Language of the generated instruction: en for English or ru for Russian. Defaults to en."
    • addedInput schema / properties / minutes / description
      Added value: +"Length of the play session in minutes. Defaults to 60."
    • addedInput schema / properties / mood / description
      Added value: +"Quest style: quick starts immediately, focus picks one clear objective, chill avoids progress pressure, and challenge asks for a difficult but reachable objective. Defaults to focus."
    • addedInput schema / properties / seed / description
      Added value: +"Optional repeatability key, up to 64 characters. The same seed plus the same normalized ordered games list selects the same game; omit it for a fresh cryptographically random choice."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "description": "A generated backlog quest plus privacy and follow-up links.",
+  "properties": {
+    "documentation_url": {
+      "description": "Human-readable API and MCP documentation.",
+      "format": "uri",
+      "type": "string"
+    },
+    "human_url": {
+      "description": "Browser version of Backlog Quest with machine-source attribution.",
+      "format": "uri",
+      "type": "string"
+    },
+    "privacy": {
+      "description": "How request data and aggregate measurement are handled.",
+      "type": "string"
+    },
+    "quest": {
+      "additionalProperties": false,
+      "description": "The selected game and the bounded play instruction.",
+      "properties": {
+        "game": {
+          "description": "The selected title from games.",
+          "type": "string"
+        },
+        "instruction": {
+          "description": "A ready-to-follow, time-boxed play instruction.",
+          "type": "string"
+        },
+        "lang": {
+          "description": "The instruction language.",
+          "type": "string"
+        },
+        "minutes": {
+          "description": "The requested session length in minutes.",
+          "type": "integer"
+        },
+        "mood": {
+          "description": "The requested quest style.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "game",
+        "minutes",
+        "mood",
+        "lang",
+        "instruction"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "quest",
+    "privacy",
+    "human_url",
+    "documentation_url"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, and the description adds material context beyond them: no account or payment required, game titles and seed processed in memory and not stored, only an aggregate request event recorded, and seed-based determinism. That disclosure of side effects and privacy behavior is exactly what an agent needs before invoking.

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?

The core purpose and the read-only guarantee are front-loaded, and the sentences on determinism, auth, and storage each carry real information. Some wording duplicates the schema's mood definitions, which is the main redundancy.

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 five-parameter generative tool with a full output schema, annotations, and complete parameter documentation, the description covers purpose, constraints, safety profile, and determinism. Nothing an agent needs to call 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 all five parameters are already documented, including mood, seed determinism, and the games list constraints. The description largely restates the schema's mood meanings and seed behavior rather than adding new semantics, so baseline 3 applies.

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: choose exactly one title from an ordered 2–12 game backlog and return the selected game plus a time-boxed instruction. It also states the boundaries (it never launches, buys, installs, modifies, or accesses a game or account), so an agent knows exactly what the tool produces 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?

The description gives concrete when-to-use context for each mode: quick to start immediately, focus for one clear objective, chill for low-pressure play, challenge for a difficult but reachable objective. There are no sibling tools, so no alternative routing is needed, but it does not state when NOT to call the tool.

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

All Backlog Quest 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