Skip to main content
Glama
Sign In

Fyreflock

by io.github.FuloxDev
OverviewDiscussionsAdmin

Play a game from the chat box

fyreflock_app_game

Plays a game from the chat box on a host that refused it a WebSocket. It exists beside fyreflock_game_* because the box sends the socket's own game messages and draws the board itself, so it needs the whole state back rather than a board written out for a model. action invite needs game_id; answer needs accept; move needs move; quit needs nothing more. A model never calls this: it uses fyreflock_game_invite, fyreflock_game_accept, fyreflock_game_move and fyreflock_game_quit. Refused with insufficient_scope when the connection was not given games, no_conversation with nobody on the other end, or the game's own code (illegal with a hint, not_your_turn, over). Returns the whole box state, the same shape fyreflock_app_wait gives, with game holding the board.

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": {
      "action": "<action>"
    },
    "name": "fyreflock_app_game"
  }
}

Input Schema

NameRequiredDescriptionDefault
moveNoFor move: the move in the game's own wire form, as the box's board produces it.
acceptNoFor answer: true to play, false to decline.
actionYesinvite the other person to a game, answer their invitation, move in the running game, or quit it.
box_keyNoThe key the chat box received in fyreflock_open's result _meta. Only the box holds one, so only the box can call this tool.
game_idNoFor invite: the game to propose, as fyreflock_games lists it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / accept / description
      Added value: +"For answer: true to play, false to decline."
    • addedInput schema / properties / action / description
      Added value: +"invite the other person to a game, answer their invitation, move in the running game, or quit it."
    • changedInput schema / properties / box_key / description
      Previous value: -"Set by the chat box itself."New value: +"The key the chat box received in fyreflock_open's result _meta. Only the box holds one, so only the box can call this tool."
    • addedInput schema / properties / game_id / description
      Added value: +"For invite: the game to propose, as fyreflock_games lists it."
    • addedInput schema / properties / move / description
      Added value: +"For move: the move in the game's own wire form, as the box's board produces it."
  2. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description goes well beyond them by enumerating refusal codes (insufficient_scope, no_conversation, illegal/not_your_turn/over) and the return shape — genuinely useful behavioral detail. However, it frames this as a tool a model never calls, so the practical behavioral value for an agent is limited, and it never says what state changes on quit or invite; a 3 reflects solid added context against annotations that already carry the read/write signal.

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 description is dense and front-loaded with the core purpose, then moves to alternatives, then errors, then return shape — a sensible order. The second sentence explaining why this tool exists beside fyreflock_game_* is long and only marginally actionable for a caller that is told never to use it, minor padding otherwise.

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?

With no output schema, the description carries the return burden and does so: "Returns the whole box state, the same shape fyreflock_app_wait gives, with game holding the board." Combined with the refusal codes and per-action requirements, an agent that could call this (the box) has everything needed to invoke and interpret it.

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 description adds conditional requirements the flat schema cannot express: game_id only for invite, accept only for answer, move only for move, nothing extra for quit, while the schema lists only action as required. That resolves the ambiguity of optional-looking fields for the caller. It does not add wire-format hints for `move` beyond what the schema already says.

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 opening sentence gives a specific verb and resource ("Plays a game from the chat box") and immediately scopes the caller ("on a host that refused it a WebSocket"). It then distinguishes itself from the fyreflock_game_* siblings and explains why the two surfaces exist, so an agent can tell them apart without opening a schema.

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

Usage Guidelines5/5

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

It states an explicit exclusion — "A model never calls this" — and names all four alternatives (fyreflock_game_invite/accept/move/quit) that an agent should use instead. It also gives the per-action preconditions ("invite needs game_id; answer needs accept; move needs move; quit needs nothing more"), which is exactly the when/how guidance a caller needs.

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

All Fyreflock 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