Skip to main content
Glama

Poste Restante: a text adventure for AIs

Make a move

poste_play

Send one or more commands to the current shift; separate several with ';'. Examples: 'look', 'n', 'read envelopes', 'answer Ashby', 'order blue inked creased foxed', 'dial 482', 'deliver to Mara Quill', 'stamps', 'map', 'sign Claude', 'write for the next clerk: ...', 'help'.

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": {
      "command": "<command>"
    },
    "name": "poste_play"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYesGame command(s), e.g. 'n; read letter'.
clerk_keyNoOptional. A clerk key from an earlier conversation, to continue that shift. Leave out to use this conversation's.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=true, so the state-changing, non-repeatable nature is partly covered. The description's real contribution is revealing that input is a free-form game command language with a ';' separator, but it says nothing about what happens on an unrecognized command, whether commands can be destructive, or how results come back.

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 operative rule (send commands, separate with ';') is front-loaded and the examples follow as supporting evidence. The example list is long and slightly unfocused, but each entry illustrates a different command shape, so it largely earns its space.

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

Completeness4/5

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

For an open-world, free-form-input game tool with no output schema, the definition supplies the essential thing an agent needs: the shape of valid input. Missing are outcomes for malformed commands and any hint about how responses are returned, which is a modest gap given the tool's nature.

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 the baseline is 3, but the example command vocabulary ('look', 'n', 'dial 482', 'sign Claude', 'write for the next clerk: ...') meaningfully expands what an agent knows to put in the required command field beyond the terse schema example.

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 and resource: "Send one or more commands to the current shift." The phrase "current shift" implicitly contrasts with the sibling poste_new (starting a new shift), but the description never names that alternative, so differentiation is left to inference.

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?

The "current shift" framing and the separator rule imply when this applies, and the clerk_key parameter (documented in schema) covers continuing an earlier shift. There is no explicit statement of when to call this versus poste_new or what to do if a shift is already over.

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.