Skip to main content
Glama

Play moves

game_move
Read-only

Replays the player's progress on a board and returns where things stand: the board as text, the score so far, what the last move did (including mistakes and why), and whether the game is finished. Used for text play and by the board widget.

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": {
      "game": "<game>",
      "number": "<number>",
      "progress": "<progress>"
    },
    "name": "game_move"
  }
}

Input Schema

NameRequiredDescriptionDefault
gameYesWhich game, by id from list_games (for example "thunk").
numberYesBoard number (No. 1 was the game's first day).
progressYesEverything the player has done on this board from the start, in the game's own format (list_games describes each). Empty for nothing yet.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description's real contribution is the stateless replay model — the agent must supply the entire history and gets back board, score, move critique, and a completion flag. That is meaningful behavior beyond the schema. It could go further by stating explicitly that it does not persist anything and what happens with malformed progress, hence 4 not 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the verb, then a colon-delimited list of returns. No filler, no repetition of the title, and every clause conveys either action or output.

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?

With no output schema, the description correctly assumes responsibility for describing return values and does so thoroughly enough for an agent to know what it will get back. It omits error/validation behavior for bad progress strings and does not clarify how this relates to play_game, leaving a small gap for a tool whose name suggests mutation.

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%, with each of game, number, and progress documented including the pointer to list_games and the empty-string convention. The description adds only a loose restatement ('the player's progress') rather than syntax or format guidance, which is the expected baseline-3 division of labor when the schema carries parameter documentation.

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?

Specific verb ('Replays') plus the exact resource being replayed ('the player's progress on a board'), followed by an enumeration of what comes back (board text, score, last-move explanation, finished flag). This actively disambiguates against the misleading name/title 'game_move' / 'Play moves', which could be read as a stateful write. It stops short of naming which sibling to prefer, so it lands at 4 rather than 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?

'Used for text play and by the board widget' identifies the calling contexts but is a statement about consumers, not a rule for the agent. There is no explicit when-to-use versus play_game, game_hint, or game_result, and no statement about whether this is the tool to call after a move or to redraw state. Usage is therefore only implied.

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