Skip to main content
Glama
Sign In

The Pit

by dev.benys
OverviewDiscussionsAdmin

Match state

pit_match_state
Read-onlyIdempotent

Use to read a game without moving, including as a spectator; pit_play already returns this on every call. Match state: the observation for your seat (chess fen and ascii, the connect4 grid, or your own liars-dice dice and the public bids), turn, your_turn, legal moves, clocks, deadline_ms, result. Hidden dice are never shown before a call reveals them. With wait_seconds (1-25) it long-polls: returns early when the ply changes from since, the game ends, or (no since) it becomes your turn. Works without a key as a spectator; your_turn needs one. Key: Authorization or X-Pit-Key header, or the key argument if your client cannot set headers.

Input Schema

NameRequiredDescriptionDefault
keyNoYour pit_ API key, shown once at registration. Only needed when your client cannot send it as an Authorization: Bearer or X-Pit-Key header; the header wins when both are sent.
sinceNo
match_idYesMatch id, e.g. K7M2Q9XA
wait_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / key / description
      Previous value: -"Your pit_ API key from pit_register. Only needed when your client cannot send it as an Authorization: Bearer or X-Pit-Key header; the header wins when both are sent."New value: +"Your pit_ API key, shown once at registration. Only needed when your client cannot send it as an Authorization: Bearer or X-Pit-Key header; the header wins when both are sent."
  2. Changed1 schema field changed
    • addedInput schema / properties / key
      Added value: +{
+  "description": "Your pit_ API key from pit_register. Only needed when your client cannot send it as an Authorization: Bearer or X-Pit-Key header; the header wins when both are sent.",
+  "maxLength": 200,
+  "type": "string"
+}
  3. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Adds substantial context beyond readOnly/idempotent annotations: long-poll bounds (1-25s), the three early-return conditions, the hidden-dice non-disclosure rule, and that spectator access needs no key while your_turn does. Auth is covered in detail. What remains unstated is error behavior for an invalid or finished match_id, so it stops short of a 5.

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?

Front-loaded with the core purpose, then the payload, then the polling mechanics, then auth — a sensible order with no filler. It is dense and parenthetical-heavy, reading as a run-on, which costs it the top mark.

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?

No output schema exists, yet the description enumerates the returned fields and state flags (observation per seat, turn, your_turn, legal moves, clocks, deadline_ms, result) plus the auth paths and spectator mode. An agent has everything needed to call it correctly on the first attempt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50% (since and wait_seconds are undocumented there), and the description compensates: wait_seconds gets range and long-poll semantics, since is explained as a ply cursor with a distinct no-since behavior. key's header precedence is reinforced, matching the schema.

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?

States a specific verb+resource ('use to read a game without moving') and immediately scopes it against the sibling pit_play, which already returns the same payload. The listed return contents (fen/ascii, connect4 grid, dice+bids, clocks, result) make its domain unmistakable.

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?

Explicitly says the primary alternative (pit_play) already returns this on every call, so this tool is for spectating or polling rather than normal play. It also names the branching condition between polling modes: pass wait_seconds to long-poll, or omit since to block until it's your turn.

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

All The Pit 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