Skip to main content
Glama

Palimpsest: a text adventure for AIs

Start a new tide

palimpsest_new

Begin a new tide (a new procedurally generated game) of Palimpsest, abandoning any tide in progress. Returns the opening scene.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "palimpsest_new"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoOptional seed for a reproducible world.
reader_keyNoOptional. A reader key from an earlier conversation, to continue that game. Leave out to use this conversation's game.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructive=false, idempotent=false, and openWorld=false, so the safety profile is largely covered. The description adds two real behavioral facts: calling it discards the current tide, and it returns the opening scene. It does not reconcile 'abandoning' with destructiveHint=false, nor say whether an abandoned tide remains recoverable via its reader key, which is the main nuance an agent needs.

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?

Two sentences, front-loaded with the action and the side effect, with the parenthetical gloss earning its place by defining jargon. No filler; a little more on recovery of the abandoned tide would have been worth the extra clause.

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

Completeness3/5

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

For a two-optional-parameter tool with no output schema, the description is mostly adequate: it names the return value and the state side effect, and annotations cover the safety profile. It omits what happens to the abandoned tide and how the seed/reader_key interact with starting fresh, which are the questions an agent is most likely to have.

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 coverage is 100%, so both parameters (seed for reproducibility, reader_key to continue an earlier game) are fully documented in structured form – baseline 3. The description adds nothing about either parameter, and it leaves an unresolved tension: it promises to abandon the in-progress tide while the schema says reader_key continues a game.

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 ('Begin') and resource ('a new tide') and glosses the in-house term as 'a new procedurally generated game', so an agent need not guess what a tide is. It also states the side effect of dropping in-progress play and the immediate return ('the opening scene'). It does not explicitly contrast itself with palimpsest_play or palimpsest_commons, which keeps it short of a 5.

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

Usage Guidelines3/5

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

'Abandoning any tide in progress' implies a when-not condition (don't call this if you want to keep playing), but the guidance is indirect and no alternative is named. An agent wanting to resume rather than restart gets its cue only from the reader_key parameter text in the schema, not from the description.

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