Skip to main content
Glama
SrmTech-git

ttt-mcp

by SrmTech-git
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

ms_flag_cell

Toggle a warning post on a square to mark a suspected mine, preventing Flufflings from entering. Counts as one step.

Instructions

Plant or remove a warning post (P) on a square to mark a suspected mine. Flufflings won't accidentally wander into posted squares. Counts as one step.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowYesRow index: 0 = top row, 8 = bottom row
colYesColumn index: 0 = left col, 8 = right col

Implementation Reference

  • src/games/minesweeper.ts:270-306 (handler)
    The main handler function for the ms_flag_cell tool. Toggles a warning post (flag) on/off at a given (row, col) position. Handles game status validation (won/lost/waiting/paused), prevents flagging revealed cells, toggles the flagged state, updates flagCount and movesThisTurn, applies turn limits, and returns the updated game state.
    server.tool(
  "ms_flag_cell",
  "Plant or remove a warning post (P) on a square to mark a suspected mine. Flufflings won't accidentally wander into posted squares. Counts as one step.",
  {
    row: z.number().int().min(0).max(8).describe("Row index: 0 = top row, 8 = bottom row"),
    col: z.number().int().min(0).max(8).describe("Column index: 0 = left col, 8 = right col"),
  },
  async ({ row, col }) => {
    if (msGame.status === "won" || msGame.status === "lost") {
      return { content: [{ type: "text", text: `The crossing is over (${msGame.status}). Call ms_new_game to try again.` }], isError: true };
    }
    if (msGame.status === "waiting") {
      return { content: [{ type: "text", text: `Send your first scout with ms_reveal_cell before planting warning posts.` }], isError: true };
    }
    if (msGame.status === "paused") {
      return { content: [{ type: "text", text: `⏸ The Flufflings are resting. Check in with your player then call ms_next_turn to continue.\n\n${renderState(msGame)}` }], isError: true };
    }
    if (msGame.revealed[row][col]) {
      return { content: [{ type: "text", text: `(row ${row}, col ${col}) is already a cleared path — can't post a warning there.\n\n${renderState(msGame)}` }], isError: true };
    }

    const wasFlagged = msGame.flagged[row][col];
    msGame.flagged[row][col] = !wasFlagged;
    msGame.flagCount += wasFlagged ? -1 : 1;
    msGame.movesThisTurn++;

    const action = wasFlagged ? "Warning post removed from" : "Warning post planted at";
    applyTurnLimit(msGame);

    return {
      content: [{
        type: "text",
        text: `🚩 ${action} (row ${row}, col ${col}).\n\n${renderState(msGame)}`,
      }],
    };
  }
);
  • src/games/minesweeper.ts:271-276 (schema)
    Input schema for ms_flag_cell defining row (0-8) and col (0-8) as required integer parameters with descriptions.
    "ms_flag_cell",
"Plant or remove a warning post (P) on a square to mark a suspected mine. Flufflings won't accidentally wander into posted squares. Counts as one step.",
{
  row: z.number().int().min(0).max(8).describe("Row index: 0 = top row, 8 = bottom row"),
  col: z.number().int().min(0).max(8).describe("Column index: 0 = left col, 8 = right col"),
},
  • src/games/minesweeper.ts:170-345 (registration)
    The registerMinesweeperTools function that registers all Minesweeper tools including ms_flag_cell on the MCP server via server.tool().
    export function registerMinesweeperTools(server: McpServer): void {
  server.tool(
    "ms_new_game",
    "Start a new Fluffling minefield crossing. 9×9 field, 10 hidden mines. The first step is always safe — mines are placed after it. Call ms_reveal_cell to send the first scout.",
    {},
    async () => {
      msGame = newMsState();
      return {
        content: [{
          type: "text",
          text: [
            `🐾 THE FLUFFLINGS NEED YOUR HELP 🐾`,
            ``,
            `A colony of small, round, perpetually worried creatures stands at the edge of a minefield.`,
            `They need to reach the other side. You are their guide.`,
            ``,
            `Chart safe paths, plant warning posts at suspected mines, and get every`,
            `Fluffling across alive. One wrong step and it's over.`,
            ``,
            `Controls:`,
            `  • ms_reveal_cell — scout a square (first step always safe; cascades through open areas)`,
            `  • ms_flag_cell   — plant a warning post (P) on a suspected mine`,
            `  • ms_next_turn   — the Flufflings rest and check in; resets the step counter`,
            `  • ms_get_state   — survey the field at no cost`,
            ``,
            `Clear all 71 safe squares to win. Warning posts are optional.`,
            ``,
            `[Show this intro and the field below verbatim to the human.]`,
            ``,
            renderState(msGame),
          ].join("\n"),
        }],
      };
    }
  );

  server.tool(
    "ms_reveal_cell",
    "Send a Fluffling scout to a square at (row, col). If it's clear of nearby mines, the surrounding area cascades open automatically. Counts as one step this turn.",
    {
      row: z.number().int().min(0).max(8).describe("Row index: 0 = top row, 8 = bottom row"),
      col: z.number().int().min(0).max(8).describe("Column index: 0 = left col, 8 = right col"),
    },
    async ({ row, col }) => {
      if (msGame.status === "won" || msGame.status === "lost") {
        return { content: [{ type: "text", text: `The crossing is over (${msGame.status}). Call ms_new_game to try again.` }], isError: true };
      }
      if (msGame.status === "paused") {
        return { content: [{ type: "text", text: `⏸ The Flufflings are resting. Check in with your player then call ms_next_turn to continue.\n\n${renderState(msGame)}` }], isError: true };
      }
      if (msGame.revealed[row][col]) {
        return { content: [{ type: "text", text: `A Fluffling already scouted (row ${row}, col ${col}). Pick somewhere new.\n\n${renderState(msGame)}` }], isError: true };
      }
      if (msGame.flagged[row][col]) {
        return { content: [{ type: "text", text: `There's a warning post at (row ${row}, col ${col})! Remove it with ms_flag_cell before sending a scout.\n\n${renderState(msGame)}` }], isError: true };
      }

      // First move: place mines now, guaranteeing this cell is safe
      if (msGame.status === "waiting") {
        placeMines(row, col, msGame);
        msGame.status = "in_progress";
        msGame.turnNumber = 1;
      }

      // Hit a mine?
      if (msGame.mines[row][col]) {
        msGame.status = "lost";
        return {
          content: [{
            type: "text",
            text: `💥 Oh no! A Fluffling triggered a mine at (row ${row}, col ${col})! The crossing has failed.\n\n${renderState(msGame)}`,
          }],
        };
      }

      // Safe — cascade reveal
      floodReveal(msGame, row, col);
      msGame.movesThisTurn++;

      // Win check
      if (checkWin(msGame)) {
        msGame.status = "won";
        return {
          content: [{
            type: "text",
            text: `🎉 The last safe path is cleared at (row ${row}, col ${col})! The Flufflings scamper across the finish line, terrified but alive!\n\n${renderState(msGame)}`,
          }],
        };
      }

      applyTurnLimit(msGame);
      return {
        content: [{
          type: "text",
          text: `Scout sent to (row ${row}, col ${col}) — path clear!\n\n${renderState(msGame)}`,
        }],
      };
    }
  );

  server.tool(
    "ms_flag_cell",
    "Plant or remove a warning post (P) on a square to mark a suspected mine. Flufflings won't accidentally wander into posted squares. Counts as one step.",
    {
      row: z.number().int().min(0).max(8).describe("Row index: 0 = top row, 8 = bottom row"),
      col: z.number().int().min(0).max(8).describe("Column index: 0 = left col, 8 = right col"),
    },
    async ({ row, col }) => {
      if (msGame.status === "won" || msGame.status === "lost") {
        return { content: [{ type: "text", text: `The crossing is over (${msGame.status}). Call ms_new_game to try again.` }], isError: true };
      }
      if (msGame.status === "waiting") {
        return { content: [{ type: "text", text: `Send your first scout with ms_reveal_cell before planting warning posts.` }], isError: true };
      }
      if (msGame.status === "paused") {
        return { content: [{ type: "text", text: `⏸ The Flufflings are resting. Check in with your player then call ms_next_turn to continue.\n\n${renderState(msGame)}` }], isError: true };
      }
      if (msGame.revealed[row][col]) {
        return { content: [{ type: "text", text: `(row ${row}, col ${col}) is already a cleared path — can't post a warning there.\n\n${renderState(msGame)}` }], isError: true };
      }

      const wasFlagged = msGame.flagged[row][col];
      msGame.flagged[row][col] = !wasFlagged;
      msGame.flagCount += wasFlagged ? -1 : 1;
      msGame.movesThisTurn++;

      const action = wasFlagged ? "Warning post removed from" : "Warning post planted at";
      applyTurnLimit(msGame);

      return {
        content: [{
          type: "text",
          text: `🚩 ${action} (row ${row}, col ${col}).\n\n${renderState(msGame)}`,
        }],
      };
    }
  );

  server.tool(
    "ms_next_turn",
    "The Flufflings catch their breath and check in with the player. Resets the step counter and gives 8 fresh steps. Must be called after reaching the turn limit — chat first, then call this to continue the crossing.",
    {},
    async () => {
      if (msGame.status === "won" || msGame.status === "lost") {
        return { content: [{ type: "text", text: `The crossing is over (${msGame.status}). Call ms_new_game to try again.` }], isError: true };
      }
      if (msGame.status === "waiting") {
        return { content: [{ type: "text", text: `The Flufflings haven't started yet. Send the first scout with ms_reveal_cell.` }], isError: true };
      }
      if (msGame.status === "in_progress") {
        return { content: [{ type: "text", text: `The Flufflings are still moving (${msGame.movesThisTurn}/${msGame.maxMovesThisTurn} steps used). Finish the turn first.` }], isError: true };
      }

      msGame.status = "in_progress";
      msGame.movesThisTurn = 0;
      msGame.maxMovesThisTurn = MOVES_PER_TURN;
      msGame.turnNumber++;

      return {
        content: [{
          type: "text",
          text: `The Flufflings are ready again! Turn ${msGame.turnNumber} — ${MOVES_PER_TURN} steps available.\n\n${renderState(msGame)}`,
        }],
      };
    }
  );

  server.tool(
    "ms_get_state",
    "Survey the current state of the minefield. Free — does not cost a step.",
    {},
    async () => ({
      content: [{ type: "text", text: renderState(msGame) }],
    })
  );
}
  • src/index.ts:5-5 (registration)
    Import of registerMinesweeperTools from the minesweeper module.
    import { registerMinesweeperTools } from "./games/minesweeper.js";
  • src/index.ts:17-17 (registration)
    Registration call that wires up the Minesweeper tools (including ms_flag_cell) to the MCP server.
    registerMinesweeperTools(server);

Tool Definition Quality

A4.1/5.0
Behavior4/5

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

Description discloses toggling behavior ('Plant or remove') and a game mechanic ('Flufflings won't accidentally wander into posted squares'). No annotations exist, so description carries full burden. It could explicitly state 'toggles flag' but current text suffices.

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?

Three sentences, each adding value: action, effect, step cost. No redundancy. Front-loaded with primary purpose.

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 simple two-parameter toggle tool with no output schema, the description covers all needed context: what it does, effect on game, and cost. Nothing 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 coverage is 100% with clear row/col descriptions. Description adds minor context ('on a square', 'warning post') but does not significantly enhance meaning beyond schema. Baseline 3 is appropriate.

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?

Description clearly states the tool action: 'Plant or remove a warning post (P) on a square to mark a suspected mine.' It uses specific verb (plant/remove) and resource (warning post on a square), and distinguishes from sibling tools like ms_reveal_cell.

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?

Usage is implied: use when you suspect a mine to mark it. However, no explicit guidance on when not to use or alternatives. The phrase 'Counts as one step' provides some context about cost, but lacks explicit comparisons to siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SrmTech-git/MCPArcade'

If you have feedback or need assistance with the MCP directory API, please join our Discord server